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

    Neuronpedia

    INDEX
    Explanations

    words related to excessive or uncontrolled behavior

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

    scribbling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    LCA
    -0.43
     CSRF
    -0.41
    CSRF
    -0.40
    MCT
    -0.39
     MCT
    -0.39
     LCA
    -0.38
     Vast
    -0.38
     Mui
    -0.37
     Hs
    -0.36
     Hyd
    -0.36
    POSITIVE LOGITS
    bble
    1.88
    bbling
    1.65
    bbles
    1.49
    bbled
    1.43
    bbler
    0.93
     հղումներ
    0.59
    rungsseite
    0.56
    曖昧さ回避
    0.53
    bber
    0.53
    rabble
    0.51
    Act Density 0.015%

    No Known Activations