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

    Neuronpedia

    INDEX
    Explanations

    emotional expressions related to loneliness and despair

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

    Japanese adjectives ending in "i" or "ra"

    np_acts-logits-general · gemini-2.0-flash

    adjectives followed by comparisons or states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     المعيارى
    -0.62
    endif
    -0.56
    Kariera
    -0.55
    OGND
    -0.55
     AssemblyProduct
    -0.52
     Principe
    -0.52
    callee
    -0.51
    ectl
    -0.51
    Hochspringen
    -0.50
    RegistryLite
    -0.49
    POSITIVE LOGITS
    issima
    0.67
    issimo
    0.67
    issime
    0.61
    한
    0.61
     Walkover
    0.58
    guro
    0.54
    yet
    0.53
    simo
    0.52
     Bau
    0.52
    sima
    0.52
    Act Density 0.110%

    No Known Activations