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

    Neuronpedia

    INDEX
    Explanations

    Code and data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /me
    -0.07
     disob
    -0.06
    ुओ
    -0.06
    cooldown
    -0.06
     facets
    -0.06
     monde
    -0.06
    _sort
    -0.06
     odpověd
    -0.06
    =model
    -0.06
     seizure
    -0.06
    POSITIVE LOGITS
    пор
    0.07
    를
    0.06
     tickets
    0.06
    .getP
    0.06
    .Paths
    0.06
     Flexible
    0.06
    (""+
    0.06
     identifying
    0.06
     Ell
    0.06
    edik
    0.06
    Act Density 0.001%

    No Known Activations