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

    Neuronpedia

    INDEX
    Explanations

    transformations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    igon
    -0.06
    oyer
    -0.06
     POT
    -0.06
     dirs
    -0.06
    apol
    -0.06
     Race
    -0.06
    .|
    -0.06
     уяв
    -0.06
     Extreme
    -0.06
     pau
    -0.06
    POSITIVE LOGITS
    (ent
    0.07
    �
    0.06
    (blog
    0.06
    997
    0.06
    .eclipse
    0.06
    .Web
    0.06
    -grade
    0.06
    _exc
    0.06
    dü
    0.06
    0.06
    Act Density 0.004%

    No Known Activations