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

    Neuronpedia

    INDEX
    Explanations

    applications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ولة
    -0.07
     script
    -0.07
     U
    -0.07
    高质量
    -0.07
    茶
    -0.06
    /backend
    -0.06
    liness
    -0.06
     finalists
    -0.06
     tutorial
    -0.06
    ァ
    -0.06
    POSITIVE LOGITS
    فائ
    0.07
     Append
    0.06
    编织
    0.06
    *>&
    0.06
    '])?
    0.06
    getDisplay
    0.06
    зов
    0.06
    LDAP
    0.06
    être
    0.06
     Sarah
    0.06
    Act Density 0.003%

    No Known Activations