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

    Neuronpedia

    INDEX
    Explanations

    Mary Magdalene

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     revers
    -0.09
     reversal
    -0.08
     cracks
    -0.08
     brutal
    -0.08
     inverted
    -0.08
    Invert
    -0.07
     ciphertext
    -0.07
     reversed
    -0.07
    950
    -0.07
     invert
    -0.07
    POSITIVE LOGITS
     companionship
    0.08
     Telefon
    0.08
     pasangan
    0.08
     친구
    0.08
     STREAM
    0.08
     Sint
    0.08
     Quelle
    0.08
     venner
    0.08
     സംഭ
    0.08
     confidentialité
    0.08
    Act Density 0.004%

    No Known Activations