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
     spirituality
    -0.07
    却是
    -0.07
    sanız
    -0.07
    pository
    -0.07
    genden
    -0.07
    了
    -0.07
    .ndarray
    -0.07
    تحضير
    -0.07
    חנו
    -0.07
    南通
    -0.07
    POSITIVE LOGITS
     wear
    0.07
     representation
    0.07
     shear
    0.07
     <<
    0.07
     Day
    0.07
     Girls
    0.07
    STE
    0.06
    DockControl
    0.06
     starring
    0.06
    amps
    0.06
    Act Density 0.003%

    No Known Activations