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

    Neuronpedia

    INDEX
    Explanations

    technical snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     TAS
    -0.08
     weighing
    -0.07
    이자
    -0.07
     graded
    -0.06
    说道
    -0.06
     concluded
    -0.06
    àu
    -0.06
    _rd
    -0.06
     corridors
    -0.06
    گوی
    -0.06
    POSITIVE LOGITS
    meteor
    0.06
    TexImage
    0.06
    .effects
    0.06
    ΙΚ
    0.06
     пищ
    0.06
     вір
    0.06
    λλ
    0.06
     رایگان
    0.06
     oyuncu
    0.06
    /vector
    0.06
    Act Density 0.000%

    No Known Activations