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

    Neuronpedia

    INDEX
    Explanations

    AC

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     AC
    -0.73
     Belt
    -0.71
    belt
    -0.67
    Belt
    -0.67
    nezeu
    -0.65
     transfieras
    -0.60
    \{\\
    -0.59
    AC
    -0.57
     Polda
    -0.57
    lapsingToolbar
    -0.57
    POSITIVE LOGITS
    picasso
    0.60
     religieuses
    0.56
    igshid
    0.56
     SUDOC
    0.53
    openzeppelin
    0.52
     päivä
    0.52
    principalColumn
    0.52
     ProtoMessage
    0.51
    paign
    0.50
     CanadaChoose
    0.49
    Act Density 0.103%

    No Known Activations