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

    Neuronpedia

    INDEX
    Explanations

    cause

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sacred
    -0.08
     No
    -0.08
     Million
    -0.07
     Percent
    -0.07
     western
    -0.07
     drama
    -0.07
    _TH
    -0.07
    bounding
    -0.06
     Inbox
    -0.06
     Stock
    -0.06
    POSITIVE LOGITS
    0.07
    inç
    0.07
    "]=>
    0.07
     인터
    0.07
    (application
    0.07
    (tile
    0.06
    0.06
    Artifact
    0.06
     użytk
    0.06
    ,false
    0.06
    Act Density 0.036%

    No Known Activations