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

    Neuronpedia

    INDEX
    Explanations

    select, selection, and searching

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     secur
    1.88
     Sec
    1.84
    Sec
    1.84
     security
    1.79
     Security
    1.71
     secure
    1.70
    Security
    1.69
    Secure
    1.68
     Secure
    1.67
    セキュリティ
    1.64
    POSITIVE LOGITS
     сер
    0.36
     ContentValues
    0.36
    enbach
    0.36
     $(-
    0.35
     elektrom
    0.35
    ūk
    0.34
     namik
    0.34
     uninhab
    0.34
    魉
    0.34
    jillo
    0.34
    Act Density 0.058%

    No Known Activations