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

    Neuronpedia

    INDEX
    Explanations

    you

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    馞
    -0.08
    欻
    -0.07
    �
    -0.07
     numéro
    -0.06
    _cells
    -0.06
    Ṗ
    -0.06
    姥
    -0.06
     make
    -0.06
     robes
    -0.06
     trebuie
    -0.06
    POSITIVE LOGITS
    /material
    0.07
    棠
    0.07
     deport
    0.07
    	admin
    0.07
    平民
    0.07
    samp
    0.06
    路虎
    0.06
    _LINUX
    0.06
    olate
    0.06
    崃
    0.06
    Act Density 0.003%

    No Known Activations