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

    Neuronpedia

    INDEX
    Explanations

    phishing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    sud
    0.47
    switching
    0.45
    tı
    0.45
    ravity
    0.44
    tan
    0.44
    ⌣
    0.43
    ifié
    0.42
     پرس
    0.42
    taking
    0.41
    solving
    0.41
    POSITIVE LOGITS
     ph
    1.03
     Ph
    1.03
    Ph
    0.89
     PH
    0.86
    ph
    0.77
     PHA
    0.77
     phishing
    0.75
     Phar
    0.74
     pha
    0.71
     Pharaoh
    0.70
    Act Density 0.026%

    No Known Activations