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

    Neuronpedia

    INDEX
    Explanations

    legal/criminal proceedings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     depiction
    -0.07
     BMI
    -0.07
    ches
    -0.07
     disgusting
    -0.06
    bara
    -0.06
    avers
    -0.06
     TRACE
    -0.06
    _owner
    -0.06
     Circus
    -0.06
    alternate
    -0.06
    POSITIVE LOGITS
     ----------------------------------------------------------------------------↵
    0.07
     ForCanBeConverted
    0.07
    ोषण
    0.06
    카라
    0.06
     أكتوبر
    0.06
    idual
    0.06
     रखत
    0.06
    (#
    0.06
    IsRequired
    0.06
     бог
    0.06
    Act Density 0.008%

    No Known Activations