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

    Neuronpedia

    INDEX
    Explanations

    names and places

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    STRACT
    -0.06
    (rgb
    -0.06
    rimp
    -0.06
     relevant
    -0.06
    �
    -0.06
     ayrı
    -0.06
    .youtube
    -0.06
    _VOLUME
    -0.06
    -important
    -0.06
    Aware
    -0.06
    POSITIVE LOGITS
     olmam
    0.07
    errupt
    0.07
    Berry
    0.06
    .AddItem
    0.06
    ependency
    0.06
    ，更
    0.06
    —you
    0.06
    .HashSet
    0.06
    /dis
    0.06
    alus
    0.06
    Act Density 0.104%

    No Known Activations