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

    Neuronpedia

    INDEX
    Explanations

    Gaining access

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ullen
    -0.07
     Pentagon
    -0.07
    160
    -0.07
     dout
    -0.06
    相
    -0.06
     villa
    -0.06
     Jury
    -0.06
     social
    -0.06
    :*
    -0.06
    Began
    -0.06
    POSITIVE LOGITS
    phy
    0.07
    .Pointer
    0.07
     liberation
    0.06
    -www
    0.06
    _StaticFields
    0.06
     HAPP
    0.06
    (gr
    0.06
     Rangers
    0.06
     우
    0.06
    yyyy
    0.06
    Act Density 0.055%

    No Known Activations