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

    Neuronpedia

    INDEX
    Explanations

    Harmful content

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     afar
    -0.08
     précieux
    -0.08
     radius
    -0.08
     EEPROM
    -0.08
     Resin
    -0.08
    Dll
    -0.08
    Actual
    -0.08
     Ler
    -0.08
     resistor
    -0.08
     parks
    -0.08
    POSITIVE LOGITS
    色情
    0.11
     sexual
    0.11
     erot
    0.11
     сексу
    0.10
     violence
    0.10
     Violence
    0.10
     pornography
    0.10
     profanity
    0.10
     hateful
    0.10
     transgender
    0.09
    Act Density 0.208%

    No Known Activations