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

    Neuronpedia

    INDEX
    Explanations

    programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Protect
    -0.07
    очно
    -0.07
     said
    -0.06
    voice
    -0.06
    stances
    -0.06
    assert
    -0.06
     voc
    -0.06
    وئ
    -0.06
    ifact
    -0.06
    ismic
    -0.06
    POSITIVE LOGITS
     Cherokee
    0.07
     Finals
    0.06
     kent
    0.06
     eligibility
    0.06
    jandro
    0.06
     handgun
    0.06
     индивиду
    0.06
     Eva
    0.06
     τις
    0.06
    �璃
    0.06
    Act Density 0.000%

    No Known Activations