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

    Neuronpedia

    INDEX
    Explanations

    have

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     が
    -0.07
     Specialty
    -0.07
     Girl
    -0.07
     alb
    -0.07
     shading
    -0.07
     Jeffrey
    -0.07
    θηκε
    -0.07
     Julius
    -0.06
    Tot
    -0.06
    sortBy
    -0.06
    POSITIVE LOGITS
     rampant
    0.06
     comando
    0.06
    屏
    0.06
    .Writer
    0.06
    _DDR
    0.06
    เคร
    0.06
    abic
    0.06
    솔
    0.06
    .addWidget
    0.06
     hairs
    0.06
    Act Density 0.018%

    No Known Activations