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

    Neuronpedia

    INDEX
    Explanations

    _s _t

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (actual
    -0.07
     irritated
    -0.07
    (msg
    -0.06
     practical
    -0.06
    νει
    -0.06
     δο
    -0.06
    _integration
    -0.06
    "),"
    -0.06
     follic
    -0.06
     perse
    -0.06
    POSITIVE LOGITS
    ìm
    0.07
    ší
    0.06
     İngilizce
    0.06
    fi
    0.06
    .sap
    0.06
     Emin
    0.06
    .AutoScaleDimensions
    0.06
     koşul
    0.06
     Marvel
    0.06
     assertNotNull
    0.06
    Act Density 0.018%

    No Known Activations