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

    Neuronpedia

    INDEX
    Explanations

    Country aid and support

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dann
    -0.07
    ’ye
    -0.06
    thumbnails
    -0.06
    regs
    -0.06
     struk
    -0.06
    ën
    -0.06
     scant
    -0.06
    604
    -0.06
    ウス
    -0.06
     vet
    -0.06
    POSITIVE LOGITS
    .Len
    0.07
     Dot
    0.06
    통
    0.06
    fortunate
    0.06
    .GetChild
    0.06
    reducers
    0.06
    );

↵
    0.06
    igrated
    0.06
     incurred
    0.06
    .NoError
    0.06
    Act Density 0.057%

    No Known Activations