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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    مال
    -0.07
    /↵↵
    -0.07
     masih
    -0.06
     cpt
    -0.06
    (chan
    -0.06
     aplik
    -0.06
     Contents
    -0.06
     compete
    -0.06
    ")↵↵
    -0.06
    GCC
    -0.06
    POSITIVE LOGITS
    Ξ
    0.07
     Immun
    0.06
     Hz
    0.06
     �
    0.06
    imers
    0.06
     سان
    0.06
     Brewery
    0.06
    ав
    0.06
     eater
    0.05
     backing
    0.05
    Act Density 0.000%

    No Known Activations