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

    Neuronpedia

    INDEX
    Explanations

    Excerpts with dialogue

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    isci
    -0.07
     Thinking
    -0.07
    اضی
    -0.07
     بك
    -0.07
    ｀ヽ
    -0.07
     tanto
    -0.06
    .community
    -0.06
     obvykle
    -0.06
    parison
    -0.06
    ез
    -0.06
    POSITIVE LOGITS
     exited
    0.06
    oppers
    0.06
     mock
    0.06
    idelity
    0.06
    ancias
    0.06
     re
    0.06
     pizza
    0.06
    Aff
    0.05
     authenticate
    0.05
     []↵↵↵
    0.05
    Act Density 0.009%

    No Known Activations