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

    Neuronpedia

    INDEX
    Explanations

    safety and detection

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Whats
    0.42
     imshow
    0.40
    Ⲥ
    0.39
     mathcolor
    0.39
    酘
    0.38
     whats
    0.37
     እየሱስ
    0.37
    Что
    0.36
     consolidation
    0.36
    cellulose
    0.36
    POSITIVE LOGITS
    :
    0.42
    iaz
    0.38
    ഴ്
    0.36
    9
    0.36
    adio
    0.35
    veen
    0.35
    ki
    0.34
    .=
    0.34
    7
    0.34
    alfi
    0.34
    Act Density 0.000%

    No Known Activations