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

    Neuronpedia

    INDEX
    Explanations

    1

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _CONNECTED
    -0.07
     XI
    -0.07
     Nora
    -0.07
    .dot
    -0.06
     Implicit
    -0.06
    lining
    -0.06
    _BOUND
    -0.06
     UNS
    -0.06
    462
    -0.06
     于
    -0.06
    POSITIVE LOGITS
    cene
    0.07
     mutually
    0.07
     brut
    0.07
    ROME
    0.06
    ウス
    0.06
     pInfo
    0.06
    크기
    0.06
     Sexy
    0.06
    ivě
    0.06
     inher
    0.06
    Act Density 0.005%

    No Known Activations