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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    tz
    -0.08
    (short
    -0.07
     nullable
    -0.07
     بع
    -0.07
    ermalink
    -0.06
    _CANCEL
    -0.06
     budd
    -0.06
     Tatto
    -0.06
    _macro
    -0.06
    Setter
    -0.06
    POSITIVE LOGITS
     explos
    0.06
     secrecy
    0.06
    东
    0.06
    :o
    0.06
     sebagai
    0.06
     <?
    0.06
     Затем
    0.06
     Lager
    0.05
     oblasti
    0.05
    _Selection
    0.05
    Act Density 0.717%

    No Known Activations