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

    Neuronpedia

    INDEX
    Explanations

    errors in code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    wins
    -0.09
    din
    -0.08
    өз
    -0.08
     symptomatic
    -0.07
    ирус
    -0.07
     Pound
    -0.07
     household
    -0.07
     novembre
    -0.07
    jid
    -0.07
     murders
    -0.07
    POSITIVE LOGITS
    対象
    0.10
    चक
    0.08
     ambigu
    0.08
     inutil
    0.08
     इच्छ
    0.08
     ambiguous
    0.08
     unmet
    0.08
     התח
    0.08
     ambiguity
    0.07
    amb
    0.07
    Act Density 0.015%

    No Known Activations