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

    Neuronpedia

    INDEX
    Explanations

    see

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    %
    -0.07
    parate
    -0.06
     format
    -0.06
    ,params
    -0.06
    cales
    -0.06
    template
    -0.06
     mut
    -0.06
    Portland
    -0.06
     cluster
    -0.06
     controlId
    -0.06
    POSITIVE LOGITS
     see
    0.16
     seen
    0.14
     saw
    0.14
     seeing
    0.12
     SEE
    0.11
    Seeing
    0.11
     Seeing
    0.11
     See
    0.11
     sees
    0.11
     Seen
    0.10
    Act Density 0.072%

    No Known Activations