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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Erin
    -0.08
     być
    -0.07
     región
    -0.07
    aseña
    -0.07
    낯
    -0.07
    athy
    -0.07
    imeInterval
    -0.06
     Bloomberg
    -0.06
     Thảo
    -0.06
    _errors
    -0.06
    POSITIVE LOGITS
    持って
    0.07
     gaping
    0.07
    particles
    0.06
     Ming
    0.06
    .element
    0.06
     coco
    0.06
     control
    0.06
     simultaneously
    0.06
    TRANSFER
    0.06
     deton
    0.06
    Act Density 0.038%

    No Known Activations