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

    Neuronpedia

    INDEX
    Explanations

    ack

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     الو
    -0.07
     의
    -0.07
     {},↵
    -0.07
    _MET
    -0.06
    ouncil
    -0.06
    電視
    -0.06
    incinnati
    -0.06
     Villa
    -0.06
     ><
    -0.06
     경북
    -0.06
    POSITIVE LOGITS
     crack
    0.16
     cracking
    0.12
     cracks
    0.12
     cracked
    0.10
     Crack
    0.10
     crackers
    0.09
     Craig
    0.09
     crackdown
    0.08
    plements
    0.07
    pray
    0.07
    Act Density 0.005%

    No Known Activations