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

    Neuronpedia

    INDEX
    Explanations

    like

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     grupos
    -0.06
     sez
    -0.06
     flaws
    -0.06
     Nom
    -0.06
    _STATS
    -0.06
     ALOG
    -0.06
     endorsing
    -0.06
    _draft
    -0.06
    �
    -0.06
    (`/
    -0.06
    POSITIVE LOGITS
    .setStatus
    0.07
    .ic
    0.07
    ่าส
    0.06
    силь
    0.06
    /*!↵
    0.06
    .Iter
    0.06
    matic
    0.06
    ptions
    0.06
    here
    0.06
     Bitcoin
    0.06
    Act Density 0.002%

    No Known Activations