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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    xor
    -0.07
    Β
    -0.06
     lift
    -0.06
    출장
    -0.06
    _af
    -0.06
    ticker
    -0.05
     Adjustment
    -0.05
    曾
    -0.05
     договору
    -0.05
    Coding
    -0.05
    POSITIVE LOGITS
    _dt
    0.07
    때
    0.07
     GA
    0.07
    oration
    0.07
    numer
    0.07
     바랍니다
    0.07
    MAL
    0.07
    antee
    0.07
    het
    0.06
    arc
    0.06
    Act Density 0.052%

    No Known Activations