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

    Neuronpedia

    INDEX
    Explanations

    oxide

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    am
    -0.07
     noon
    -0.07
    �
    -0.06
    aw
    -0.06
    AM
    -0.06
    tk
    -0.06
    aman
    -0.06
     ",",
    -0.06
     уч
    -0.06
    an
    -0.06
    POSITIVE LOGITS
    ide
    0.09
     oxide
    0.09
     viruses
    0.08
     dise
    0.08
    ADO
    0.08
     dues
    0.07
     فی
    0.07
    _FLOAT
    0.07
     Verde
    0.07
    loe
    0.07
    Act Density 0.031%

    No Known Activations