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

    Neuronpedia

    INDEX
    Explanations

    parentheses and periods

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     해야
    -0.07
     dependence
    -0.07
     sieve
    -0.07
    *K
    -0.07
    Seq
    -0.06
     PRIV
    -0.06
    Hallo
    -0.06
     geile
    -0.06
    -high
    -0.06
    ольз
    -0.06
    POSITIVE LOGITS
    _CACHE
    0.07
     ++$
    0.07
    .onChange
    0.06
     Sync
    0.06
     ridic
    0.06
    _BY
    0.06
    /views
    0.06
    .YES
    0.06
    hana
    0.06
    CCI
    0.06
    Act Density 0.101%

    No Known Activations