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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     stating
    -0.06
     školy
    -0.06
     systému
    -0.06
     Slo
    -0.06
    MOVE
    -0.06
    itable
    -0.06
     últ
    -0.06
    _Speed
    -0.06
    Within
    -0.05
    ModelState
    -0.05
    POSITIVE LOGITS
     poetic
    0.08
     hair
    0.07
    ляється
    0.07
     να
    0.06
    <char
    0.06
     girlfriend
    0.06
     il
    0.06
     Fehler
    0.06
     Travel
    0.06
    _disable
    0.06
    Act Density 0.001%

    No Known Activations