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

    Neuronpedia

    INDEX
    Explanations

    Swift package descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    㫰
    -0.07
    잽
    -0.07
    TemplateName
    -0.07
     RAF
    -0.07
    stroke
    -0.06
    덯
    -0.06
    ביטחון
    -0.06
    流浪
    -0.06
    inski
    -0.06
     strains
    -0.06
    POSITIVE LOGITS
     inhibit
    0.08
    机关
    0.08
     Olympics
    0.07
     Peripheral
    0.07
     Cosmetic
    0.07
    パソコン
    0.07
    ?"↵
    0.07
     supervision
    0.07
    Preferences
    0.07
     adorable
    0.07
    Act Density 0.078%

    No Known Activations