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

    Neuronpedia

    INDEX
    Explanations

    influence and control

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -----↵↵
    -0.07
     Billion
    -0.07
     вв
    -0.07
    Velocity
    -0.07
     Scor
    -0.07
    idia
    -0.07
     Salv
    -0.07
     workload
    -0.06
     Schultz
    -0.06
     wicked
    -0.06
    POSITIVE LOGITS
    .column
    0.06
    ([]*
    0.06
    "))
    0.06
    (func
    0.06
    aviour
    0.06
    .blob
    0.06
    .LOG
    0.06
     QHBoxLayout
    0.05
    (layers
    0.05
    rocessing
    0.05
    Act Density 0.021%

    No Known Activations