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

    Neuronpedia

    INDEX
    Explanations

    help

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ndef
    -0.07
    zan
    -0.07
    during
    -0.07
    arges
    -0.06
    lates
    -0.06
    Maker
    -0.06
     Retrieve
    -0.06
    etic
    -0.06
     Trek
    -0.06
    dw
    -0.06
    POSITIVE LOGITS
    Est
    0.07
    樹
    0.06
    _TICK
    0.06
     phenomena
    0.06
     지방
    0.06
    /report
    0.06
     texto
    0.06
    اة
    0.06
    �
    0.06
    ionales
    0.06
    Act Density 0.030%

    No Known Activations