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

    Neuronpedia

    INDEX
    Explanations

    can

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    race
    -0.07
     Matthews
    -0.06
     horizontal
    -0.06
     neighbor
    -0.06
     elde
    -0.06
    _resp
    -0.06
    Finish
    -0.06
     л
    -0.06
    iji
    -0.06
     ELSE
    -0.06
    POSITIVE LOGITS
    Denied
    0.07
    rasing
    0.06
     empath
    0.06
    ическая
    0.06
     Jeep
    0.06
    ربية
    0.06
     impart
    0.06
     Plantae
    0.06
     MyClass
    0.06
    哈
    0.06
    Act Density 0.008%

    No Known Activations