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

    Neuronpedia

    INDEX
    Explanations

    Feelings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     swords
    -0.09
    translator
    -0.07
    냨
    -0.07
     scissors
    -0.07
     coma
    -0.06
     stagger
    -0.06
    โรงพ
    -0.06
    滚动
    -0.06
    冰冷
    -0.06
    ources
    -0.06
    POSITIVE LOGITS
    )+(
    0.07
    !↵↵
    0.07
    fault
    0.07
     Hiring
    0.07
     Beyond
    0.07
    bas
    0.07
    ott
    0.06
    >L
    0.06
    construct
    0.06
    +(
    0.06
    Act Density 0.091%

    No Known Activations