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

    Neuronpedia

    INDEX
    Explanations

    d

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _SUP
    -0.07
    weep
    -0.06
    lopen
    -0.06
    allo
    -0.06
     sắp
    -0.06
    Home
    -0.06
    oog
    -0.06
    íky
    -0.06
    탕
    -0.06
     biến
    -0.06
    POSITIVE LOGITS
     Defendant
    0.07
     pleaded
    0.07
     Suggestions
    0.07
    fff
    0.06
     Political
    0.06
    maxlength
    0.06
     DNS
    0.06
    ewear
    0.06
     vzděl
    0.06
     allegedly
    0.06
    Act Density 0.001%

    No Known Activations