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

    Neuronpedia

    INDEX
    Explanations

    ()

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ده
    -0.07
    orthy
    -0.06
    peated
    -0.06
    Birth
    -0.06
    ilio
    -0.06
    不可
    -0.06
    orias
    -0.06
     chubby
    -0.06
    select
    -0.06
     northeast
    -0.06
    POSITIVE LOGITS
    toHaveLength
    0.07
    preter
    0.07
     چگونه
    0.07
     aluno
    0.07
     yeast
    0.06
     ticking
    0.06
    -ex
    0.06
    /year
    0.06
    >tagger
    0.06
     thigh
    0.06
    Act Density 0.102%

    No Known Activations