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

    Neuronpedia

    INDEX
    Explanations

    code explanations and error handling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     抗
    0.79
    ants
    0.71
     synonyms
    0.70
     antir
    0.69
     peter
    0.69
    ⁷
    0.69
     Lay
    0.68
    0.68
     Pé
    0.67
     PETER
    0.67
    POSITIVE LOGITS
     solves
    0.87
    कोड
    0.79
    Sign
    0.77
     fixes
    0.75
    Logic
    0.73
    Power
    0.72
    Fix
    0.72
    Solving
    0.71
    codigo
    0.70
    實際上
    0.69
    Act Density 0.053%

    No Known Activations