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

    Neuronpedia

    INDEX
    Explanations

    Commit

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /action
    -0.08
    .YES
    -0.07
    塑胶
    -0.07
    anco
    -0.07
    询问
    -0.06
    視
    -0.06
    onest
    -0.06
    拇指
    -0.06
     Developed
    -0.06
     bubbles
    -0.06
    POSITIVE LOGITS
    僇
    0.08
     jumped
    0.08
     Leafs
    0.07
     perpetrated
    0.07
    掳
    0.07
     Wak
    0.07
    .Dictionary
    0.07
    чист
    0.07
    luğun
    0.07
    _glyph
    0.07
    Act Density 0.007%

    No Known Activations