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

    Neuronpedia

    INDEX
    Explanations

    analyses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Orthodox
    -0.08
    Worldwide
    -0.08
     honor
    -0.08
     Victoria
    -0.08
     honorable
    -0.07
    Len
    -0.07
     सल
    -0.07
    融合
    -0.07
     comer
    -0.07
     award
    -0.07
    POSITIVE LOGITS
     sensitivity
    0.17
    Sensitivity
    0.16
     sensitiv
    0.15
     Sens
    0.14
     sensibilidad
    0.14
     sensit
    0.13
     sensitive
    0.13
     संव
    0.12
    敏
    0.12
     حساس
    0.12
    Act Density 0.010%

    No Known Activations