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

    Neuronpedia

    INDEX
    Explanations

    .S

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /by
    -0.08
    ummies
    -0.07
    _RS
    -0.07
     tariffs
    -0.07
    איזה
    -0.06
    td
    -0.06
    骈
    -0.06
    ﰿ
    -0.06
    久久
    -0.06
     pursuing
    -0.06
    POSITIVE LOGITS
     לך
    0.07
    _ant
    0.06
    esthetic
    0.06
    Duplicate
    0.06
    百万
    0.06
     cinematic
    0.06
     child
    0.06
    -stat
    0.06
    >>>
    0.06
     lesbian
    0.06
    Act Density 0.000%

    No Known Activations