Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    programming-related elements such as function definitions and commands

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Programming language, code, and data structures

    np_acts-logits-general · gemini-2.0-flash

    code and technical documentation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    windowFixed
    -0.67
    ztály
    -0.57
    ised
    -0.55
    aras
    -0.55
    virons
    -0.53
     pol
    -0.52
     Bra
    -0.52
     club
    -0.51
    adak
    -0.51
    jul
    -0.50
    POSITIVE LOGITS
    UIControlState
    0.76
     חיצוניים
    0.72
    antMatchers
    0.71
     <=",
    0.69
    __).
    0.68
    Personensuche
    0.66
    ]")]
    0.65
    hoeddwyd
    0.65
    enumi
    0.64
     Reproduce
    0.64
    Act Density 0.343%

    No Known Activations