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

    Neuronpedia

    INDEX
    Explanations

    Corrections/hesitations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     effortless
    -0.07
    рім
    -0.07
    .Serializable
    -0.07
     dislike
    -0.06
    оступ
    -0.06
    ffen
    -0.06
     offender
    -0.06
    542
    -0.06
    ";
    -0.06
    엘
    -0.06
    POSITIVE LOGITS
    uations
    0.07
    ёт
    0.06
    	video
    0.06
     masturb
    0.06
     Dover
    0.06
    .ps
    0.06
     Generates
    0.06
     목
    0.06
     sculpt
    0.06
     travelling
    0.06
    Act Density 0.020%

    No Known Activations