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

    Neuronpedia

    INDEX
    Explanations

    amazon product urls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    itic
    0.91
    propelled
    0.85
    rach
    0.82
    onge
    0.80
    lines
    0.80
    agents
    0.78
     Blaine
    0.77
    rda
    0.77
    weg
    0.77
    گن
    0.77
    POSITIVE LOGITS
     Mat
    0.76
     Commitment
    0.72
     Mats
    0.69
     commit
    0.69
    COMMIT
    0.68
    Mat
    0.66
    ULL
    0.66
    Commit
    0.64
    მატ
    0.63
     বিদ
    0.63
    Act Density 0.003%

    No Known Activations