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

    Neuronpedia

    INDEX
    Explanations

    off

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Batt
    -0.07
    -hidden
    -0.07
    aan
    -0.07
    achable
    -0.07
    选择
    -0.07
    加班
    -0.07
    alice
    -0.07
    -ad
    -0.07
    accessible
    -0.07
    InstanceState
    -0.07
    POSITIVE LOGITS
    matic
    0.07
     товар
    0.06
    كورونا
    0.06
    �
    0.06
     UCS
    0.06
    .literal
    0.06
     visibly
    0.06
    牠
    0.06
    _sa
    0.06
     Defensive
    0.06
    Act Density 0.025%

    No Known Activations