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

    Neuronpedia

    INDEX
    Explanations

    command

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Jakob
    -0.08
    _CH
    -0.08
     mil
    -0.07
    maf
    -0.07
     neglected
    -0.07
    CRI
    -0.07
    &w
    -0.07
    Parameter
    -0.07
     Sesame
    -0.07
    edeut
    -0.07
    POSITIVE LOGITS
     headquarters
    0.11
     цент
    0.10
    /control
    0.10
     केंद
    0.09
    .Control
    0.09
     dissemination
    0.09
     центра
    0.09
     координ
    0.09
     hierarchy
    0.08
     控
    0.08
    Act Density 0.005%

    No Known Activations