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

    Neuronpedia

    INDEX
    Explanations

    ="">

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    bags
    -0.07
    watch
    -0.07
    -boy
    -0.06
    男子
    -0.06
    title
    -0.06
    ide
    -0.06
    أس
    -0.06
     cage
    -0.06
     Pride
    -0.06
    atchewan
    -0.06
    POSITIVE LOGITS
     Shuttle
    0.08
     Vanessa
    0.06
    VENT
    0.06
     akce
    0.06
    AND
    0.06
     Almanya
    0.06
    -On
    0.06
    _FAST
    0.06
     learns
    0.06
     Tem
    0.06
    Act Density 0.000%

    No Known Activations