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

    Neuronpedia

    INDEX
    Explanations

    Proper nouns, technical

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    alto
    -0.07
    reatment
    -0.07
    ropic
    -0.07
     dense
    -0.07
    �
    -0.06
    ENTA
    -0.06
    เท
    -0.06
     Twe
    -0.06
     stunt
    -0.06
     aides
    -0.06
    POSITIVE LOGITS
     propri
    0.07
     Pollution
    0.07
    JSGlobalScope
    0.06
     Chromium
    0.06
    liga
    0.06
     strcpy
    0.06
     SSR
    0.06
     천
    0.06
    CustomLabel
    0.06
     dolu
    0.06
    Act Density 0.068%

    No Known Activations