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

    Neuronpedia

    INDEX
    Explanations

    AI

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (bucket
    -0.07
    _PD
    -0.07
    fdf
    -0.07
    -town
    -0.07
     fleets
    -0.07
    movement
    -0.07
    ADF
    -0.06
     redevelopment
    -0.06
     murderous
    -0.06
    illery
    -0.06
    POSITIVE LOGITS
    $log
    0.07
     Inspir
    0.06
     Laurie
    0.06
    Unc
    0.06
    یزات
    0.06
     знаком
    0.06
     Jens
    0.06
     slippery
    0.06
     Geoffrey
    0.06
    з
    0.06
    Act Density 0.034%

    No Known Activations