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
     fus
    -0.07
     Crist
    -0.06
    EST
    -0.06
     Dum
    -0.06
     divul
    -0.06
    \uc
    -0.06
     IST
    -0.06
     just
    -0.06
    acob
    -0.06
    est
    -0.06
    POSITIVE LOGITS
     Salesforce
    0.07
    ラン
    0.06
     платеж
    0.06
    (Location
    0.06
    成本
    0.06
    leftrightarrow
    0.06
     suggesting
    0.06
    erville
    0.06
     thành
    0.06
    ,,,,,,,,
    0.06
    Act Density 0.011%

    No Known Activations