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

    Neuronpedia

    INDEX
    Explanations

    Numbers ending in zero

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -Co
    -0.07
     courageous
    -0.06
     robes
    -0.06
    (character
    -0.06
     startDate
    -0.06
    iculty
    -0.06
     profund
    -0.06
    decay
    -0.06
    topl
    -0.06
    .Wh
    -0.06
    POSITIVE LOGITS
    alia
    0.08
     sedm
    0.07
     Donne
    0.06
    जर
    0.06
     Wr
    0.06
     vitam
    0.06
     kombin
    0.06
     circumcision
    0.06
    undai
    0.06
    Uni
    0.06
    Act Density 0.009%

    No Known Activations