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

    Neuronpedia

    INDEX
    Explanations

    adjectives

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Dump
    -0.07
     downstairs
    -0.06
    unakan
    -0.06
     Dynamics
    -0.06
     花
    -0.06
     anglais
    -0.06
    했
    -0.06
     Germans
    -0.06
     شيء
    -0.06
    Ross
    -0.06
    POSITIVE LOGITS
    ;)
    0.07
     illusions
    0.06
     speaking
    0.06
    ,)
    0.06
     Corinth
    0.06
     elementType
    0.06
     celebr
    0.06
     dismiss
    0.06
     역사
    0.06
     Assert
    0.06
    Act Density 0.056%

    No Known Activations