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
    器
    -0.08
     radiator
    -0.07
     `%
    -0.06
    _platform
    -0.06
    _auto
    -0.06
     light
    -0.06
    licken
    -0.06
     Manning
    -0.06
    _integral
    -0.06
     suất
    -0.06
    POSITIVE LOGITS
     songwriter
    0.07
     aracılığıyla
    0.07
    bard
    0.06
    .Constant
    0.06
     harmony
    0.06
    лерг
    0.06
    	extern
    0.06
     xor
    0.06
     azt
    0.06
     ()=>{↵
    0.06
    Act Density 0.041%

    No Known Activations