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

    Neuronpedia

    INDEX
    Explanations

    percentages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    nama
    -0.07
    (rule
    -0.07
    arem
    -0.07
    _energy
    -0.06
    ात
    -0.06
    .sam
    -0.06
    „ظ
    -0.06
    ToStr
    -0.06
    stration
    -0.06
    MM
    -0.06
    POSITIVE LOGITS
    Copying
    0.07
    Luckily
    0.07
    Prompt
    0.06
     scratched
    0.06
    ucked
    0.06
     both
    0.06
    TERN
    0.06
     promptly
    0.06
     narratives
    0.06
     hızlı
    0.06
    Act Density 0.006%

    No Known Activations