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

    Neuronpedia

    INDEX
    Explanations

    include

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    εφ
    -0.07
    antar
    -0.06
     Syria
    -0.06
    olla
    -0.06
    -space
    -0.06
    Made
    -0.06
    liced
    -0.06
    Examples
    -0.06
     repeat
    -0.06
     Collins
    -0.06
    POSITIVE LOGITS
    เธ
    0.07
     texture
    0.07
     official
    0.07
     exactly
    0.07
    (ROOT
    0.07
     advise
    0.07
    Analy
    0.07
     مات
    0.06
     theoret
    0.06
    (),
    0.06
    Act Density 0.036%

    No Known Activations