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

    Neuronpedia

    INDEX
    Explanations

    control, action

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     controlled
    -0.65
    cèse
    -0.63
     shot
    -0.61
    Pty
    -0.59
    atemala
    -0.57
     Shot
    -0.55
    transcript
    -0.51
    perfor
    -0.51
    WAUKEE
    -0.50
    avn
    -0.50
    POSITIVE LOGITS
    LookAnd
    0.69
    rungsseite
    0.69
     kasarigan
    0.65
    autant
    0.59
     invokingState
    0.59
     autorytatywna
    0.54
    IntoConstraints
    0.52
     majeurs
    0.52
    Šaltiniai
    0.51
    ┘
    0.50
    Act Density 0.157%

    No Known Activations