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

    Neuronpedia

    INDEX
    Explanations

    anything

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    tör
    -0.07
    в
    -0.07
    twenty
    -0.07
    ến
    -0.06
    ター
    -0.06
    𝐡
    -0.06
     bite
    -0.06
    _cursor
    -0.06
    posit
    -0.06
    ㉳
    -0.06
    POSITIVE LOGITS
     AAC
    0.08
    ocl
    0.08
    하며
    0.07
     `'
    0.07
     airspace
    0.07
    AAC
    0.07
     ='
    0.07
     cộng
    0.07
     uncertainty
    0.07
    athe
    0.07
    Act Density 0.001%

    No Known Activations