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

    Neuronpedia

    INDEX
    Explanations

    ic

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     additives
    -0.06
    ский
    -0.06
     Brands
    -0.06
    贫
    -0.06
    tet
    -0.06
     brown
    -0.06
    inbox
    -0.06
    */}↵
    -0.05
    iji
    -0.05
     progressives
    -0.05
    POSITIVE LOGITS
    ~/
    0.07
    _cp
    0.07
    ,%
    0.07
     lengthy
    0.06
    Tipo
    0.06
     소개
    0.06
     explanatory
    0.06
    -chat
    0.06
     dissolved
    0.06
    .drop
    0.06
    Act Density 0.003%

    No Known Activations