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

    Neuronpedia

    INDEX
    Explanations

    subjectivity and objectivity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     inscrire
    -0.09
     ansanm
    -0.08
     respir
    -0.08
     empregos
    -0.08
     Certificates
    -0.08
     Dessa
    -0.08
    طلق
    -0.08
     wrist
    -0.08
    高清视频
    -0.08
    .Documents
    -0.08
    POSITIVE LOGITS
     biases
    0.18
     bias
    0.16
     biased
    0.15
    _bias
    0.14
     Bias
    0.14
    Bias
    0.14
    biased
    0.14
    .bias
    0.14
    bias
    0.14
     biais
    0.13
    Act Density 0.047%

    No Known Activations