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

    Neuronpedia

    INDEX
    Explanations

    ji

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    uar
    -0.08
     Roch
    -0.06
    hz
    -0.06
    metrics
    -0.06
    cap
    -0.06
    ệu
    -0.06
    _rr
    -0.06
    rather
    -0.06
    iT
    -0.06
     scar
    -0.06
    POSITIVE LOGITS
    ground
    0.07
    POCH
    0.07
     článku
    0.07
     Нов
    0.07
    Translator
    0.06
    -share
    0.06
    IBE
    0.06
     Underground
    0.06
     Johns
    0.06
    JM
    0.06
    Act Density 0.031%

    No Known Activations