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

    Neuronpedia

    INDEX
    Explanations

    about/on

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    794
    -0.06
    Pieces
    -0.06
    ork
    -0.06
     nurt
    -0.06
     Cherokee
    -0.06
     P
    -0.06
    Φ
    -0.06
    .AddModelError
    -0.06
     Colo
    -0.06
    illi
    -0.05
    POSITIVE LOGITS
     sanction
    0.08
    _group
    0.07
    _REFER
    0.07
     shiny
    0.07
     объек
    0.07
     weblog
    0.07
    .sale
    0.07
    /rem
    0.07
    osexual
    0.06
    _clusters
    0.06
    Act Density 0.073%

    No Known Activations