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

    Neuronpedia

    INDEX
    Explanations

    cell stimulation and toxins

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Child
    -0.08
     Fried
    -0.07
    15
    -0.06
     whe
    -0.06
    Fish
    -0.06
    �
    -0.06
    _route
    -0.06
     consist
    -0.06
    _months
    -0.06
    双
    -0.06
    POSITIVE LOGITS
     allowance
    0.06
     ''↵
    0.06
     yeah
    0.06
     bát
    0.06
    -random
    0.06
     #=>
    0.06
    ushman
    0.06
    وی
    0.06
    SCORE
    0.06
    ！！
    0.06
    Act Density 0.135%

    No Known Activations