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

    Neuronpedia

    INDEX
    Explanations

    abuse or exploitation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    €™
    0.63
    execute
    0.48
     supon
    0.47
    addEnemy
    0.47
    imh
    0.47
    arrivalTime
    0.47
    ्हान
    0.46
    }.
    0.46
     NONINFRINGEMENT
    0.46
    elize
    0.46
    POSITIVE LOGITS
     Ab
    0.77
     ab
    0.73
     Abuse
    0.71
    Ab
    0.66
    Abstraction
    0.64
     abuse
    0.61
     abuso
    0.60
     abbey
    0.57
     Aber
    0.57
     اب
    0.55
    Act Density 0.058%

    No Known Activations