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

    Neuronpedia

    INDEX
    Explanations

    he

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    utility
    -0.07
    感情
    -0.06
    modes
    -0.06
    振
    -0.06
     refrain
    -0.06
    ervice
    -0.06
     vitam
    -0.06
     мы
    -0.06
    FLASH
    -0.06
    wrap
    -0.06
    POSITIVE LOGITS
     Estr
    0.06
    \">"
    0.06
     ASD
    0.06
    алеж
    0.06
    -dist
    0.06
    ankan
    0.06
    letal
    0.06
    (',
    0.06
    roat
    0.06
    .SQL
    0.06
    Act Density 0.127%

    No Known Activations