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

    Neuronpedia

    INDEX
    Explanations

    Contractions with "not"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    脑
    -0.08
    آمد
    -0.07
    آ
    -0.07
     δια
    -0.07
    idelberg
    -0.07
     قال
    -0.06
     степ
    -0.06
     apis
    -0.06
     therap
    -0.06
     گونه
    -0.06
    POSITIVE LOGITS
     wont
    0.11
     cannot
    0.10
    't
    0.10
    ’t
    0.09
    ’T
    0.09
     will
    0.09
     WILL
    0.08
     Wet
    0.07
     would
    0.07
    .One
    0.07
    Act Density 0.024%

    No Known Activations