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

    Neuronpedia

    INDEX
    Explanations

    .-

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     "==
    -0.08
    <Course
    -0.07
    に基
    -0.07
     ^=
    -0.07
     COURT
    -0.07
    coln
    -0.07
     councillor
    -0.07
    [column
    -0.07
    廿
    -0.07
    殣
    -0.07
    POSITIVE LOGITS
    repositories
    0.07
    تلف
    0.07
    تحضير
    0.07
    -orange
    0.07
     undergo
    0.07
    Translator
    0.07
     후
    0.07
    cm
    0.06
     defamation
    0.06
     comfort
    0.06
    Act Density 0.003%

    No Known Activations