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

    Neuronpedia

    INDEX
    Explanations

    comparisons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    antaranya
    -0.83
     avoient
    -0.79
     auroit
    -0.79
     étoient
    -0.79
    rrggbb
    -0.77
    testify
    -0.77
     feroit
    -0.76
     חיצוניים
    -0.74
     ainfi
    -0.74
    MergeFrom
    -0.73
    POSITIVE LOGITS
     not
    0.84
     NOT
    0.59
     no
    0.57
     Not
    0.53
    NOT
    0.50
     nom
    0.48
    not
    0.47
     nicht
    0.46
     không
    0.45
     nie
    0.45
    Act Density 0.000%

    No Known Activations