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

    Neuronpedia

    INDEX
    Explanations

    normally

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Received
    -0.07
    腕
    -0.07
     انج
    -0.07
     hayal
    -0.07
     Republican
    -0.07
     Мик
    -0.06
    ngr
    -0.06
    .operator
    -0.06
    _scalar
    -0.06
     �
    -0.06
    POSITIVE LOGITS
     Deferred
    0.07
     create
    0.06
    _blocks
    0.06
     Simple
    0.06
    (href
    0.06
     cracked
    0.06
     Schro
    0.06
    .VK
    0.06
     Toyota
    0.06
     Monterey
    0.06
    Act Density 0.002%

    No Known Activations