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

    Neuronpedia

    INDEX
    Explanations

    supporting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    PLIC
    -0.07
    <stdlib
    -0.07
    Label
    -0.07
    ᅨ
    -0.06
     ''↵
    -0.06
    瀔
    -0.06
    stdio
    -0.06
    amura
    -0.06
    Requests
    -0.06
    胆固醇
    -0.06
    POSITIVE LOGITS
     hc
    0.07
     bearings
    0.07
     combine
    0.07
     ent
    0.07
     وإ
    0.07
     debido
    0.07
     얼마나
    0.07
    ’in
    0.07
    oted
    0.07
     coron
    0.07
    Act Density 0.100%

    No Known Activations