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

    Neuronpedia

    INDEX
    Explanations

    reported

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    enario
    -0.07
    orf
    -0.06
    .ali
    -0.06
    -wrap
    -0.06
    IP
    -0.06
     Sick
    -0.06
     Harris
    -0.06
    dsp
    -0.06
     creature
    -0.06
     fanatic
    -0.06
    POSITIVE LOGITS
     Stars
    0.07
    (groups
    0.07
     penis
    0.07
     Abstract
    0.07
     svenska
    0.06
    .deleted
    0.06
    -earth
    0.06
    �
    0.06
    の上
    0.06
    "One
    0.06
    Act Density 0.042%

    No Known Activations