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

    Neuronpedia

    INDEX
    Explanations

    filename

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     slips
    -0.07
     whereas
    -0.06
     ModelRenderer
    -0.06
     Rohing
    -0.06
     knockout
    -0.06
     jas
    -0.06
    浩
    -0.06
    rezent
    -0.06
    屆
    -0.06
    。但
    -0.06
    POSITIVE LOGITS
    0.06
    .google
    0.06
     код
    0.06
     slander
    0.06
    esi
    0.06
     号
    0.06
    Timestamp
    0.06
    -bind
    0.06
    .Create
    0.06
    МО
    0.06
    Act Density 0.000%

    No Known Activations