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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     amber
    -0.07
    Sem
    -0.06
    /O
    -0.06
    -present
    -0.06
     Rail
    -0.06
    April
    -0.06
     twisting
    -0.06
    واهد
    -0.06
    لام
    -0.06
     увелич
    -0.06
    POSITIVE LOGITS
    iste
    0.07
     Boise
    0.07
     tolerant
    0.06
    plugin
    0.06
    候
    0.06
    enable
    0.06
    eştir
    0.06
    agic
    0.06
    jured
    0.06
     इत
    0.06
    Act Density 0.000%

    No Known Activations