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

    Neuronpedia

    INDEX
    Explanations

    say citation markers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    akış
    -0.07
    bru
    -0.07
    oulos
    -0.06
     lui
    -0.06
    	UINT
    -0.06
    oking
    -0.06
    浓厚
    -0.06
    stinian
    -0.06
    Ỡ
    -0.06
     anger
    -0.06
    POSITIVE LOGITS
     '#
    0.07
    _slider
    0.07
    干事
    0.06
     depths
    0.06
    regions
    0.06
     lf
    0.06
    -mort
    0.06
     melt
    0.06
     "#
    0.06
     carries
    0.06
    Act Density 0.003%

    No Known Activations