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

    Neuronpedia

    INDEX
    Explanations

    Technical documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    hang
    -0.06
     guerra
    -0.06
     opioids
    -0.06
     Pam
    -0.06
     자동차
    -0.06
     IsActive
    -0.06
     cousins
    -0.06
    :@"
    -0.06
    바이
    -0.06
     şöyle
    -0.06
    POSITIVE LOGITS
     redemption
    0.07
    лиз
    0.06
     deadline
    0.06
    _office
    0.06
    ールド
    0.06
     Seasons
    0.06
    _weak
    0.06
    ENS
    0.06
    ологіч
    0.06
    +len
    0.06
    Act Density 0.004%

    No Known Activations