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

    Neuronpedia

    INDEX
    Explanations

    err

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tough
    -0.07
    Birth
    -0.06
    Directories
    -0.06
    ्रम
    -0.06
    ामक
    -0.06
     subtraction
    -0.06
    .magic
    -0.06
    ьогод
    -0.06
    /images
    -0.05
    sts
    -0.05
    POSITIVE LOGITS
     want
    0.07
     recently
    0.07
    υ
    0.06
     invite
    0.06
    outing
    0.06
    %'
    0.06
     way
    0.06
    (mu
    0.06
    WG
    0.06
     Ley
    0.06
    Act Density 0.002%

    No Known Activations