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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    list
    -0.07
     Bern
    -0.06
    �
    -0.06
    ゲ
    -0.06
    _EP
    -0.06
    [k
    -0.06
     chem
    -0.06
     estud
    -0.06
    jack
    -0.06
    ()"↵
    -0.06
    POSITIVE LOGITS
     affordability
    0.08
    .bootstrapcdn
    0.07
    (HttpContext
    0.07
    twitter
    0.07
     kilomet
    0.07
     граж
    0.07
    _versions
    0.07
    (+
    0.07
     nevy
    0.07
     Πολι
    0.06
    Act Density 0.161%

    No Known Activations