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

    Neuronpedia

    INDEX
    Explanations

    ol

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     الخ
    -0.06
     �
    -0.06
     Stay
    -0.06
    hunt
    -0.06
    _phi
    -0.06
    --------
    -0.06
     Writers
    -0.06
    uda
    -0.05
    Anderson
    -0.05
    ut
    -0.05
    POSITIVE LOGITS
    abolic
    0.08
    พร
    0.07
    ерти
    0.07
    jící
    0.07
    .life
    0.06
     AccessToken
    0.06
     accel
    0.06
    ableOpacity
    0.06
    -dr
    0.06
    olic
    0.06
    Act Density 0.001%

    No Known Activations