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

    Neuronpedia

    INDEX
    Explanations

    US states

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .getApp
    -0.07
     nisi
    -0.07
    Х
    -0.07
    _HTTP
    -0.06
    猜
    -0.06
    (btn
    -0.06
    ी,
    -0.06
    �
    -0.06
     Editing
    -0.06
    _regeneration
    -0.06
    POSITIVE LOGITS
     vnitř
    0.07
    gew
    0.07
     nov
    0.06
    pression
    0.06
     systemctl
    0.06
    inals
    0.06
     Decide
    0.06
    ochastic
    0.06
     routed
    0.06
    ylv
    0.06
    Act Density 0.030%

    No Known Activations