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

    Neuronpedia

    INDEX
    Explanations

    Foreign languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     стру
    -0.08
    そして
    -0.07
    _hit
    -0.07
     show's
    -0.07
    ої
    -0.07
    หย
    -0.07
    直到
    -0.07
    jg
    -0.07
    jobs
    -0.07
     hij
    -0.07
    POSITIVE LOGITS
     accompanies
    0.18
     accompany
    0.18
     accompanying
    0.16
    伴
    0.16
     accompanied
    0.15
     accompagn
    0.15
     accompaniment
    0.14
     acompañado
    0.14
     accompagné
    0.14
     accompagne
    0.14
    Act Density 0.096%

    No Known Activations