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

    Neuronpedia

    INDEX
    Explanations

    mechanical principles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ሃ
    0.41
     ViewData
    0.40
    氦
    0.40
    ::$
    0.40
    emplate
    0.38
     haste
    0.38
    :%
    0.37
     exponential
    0.37
     аутох
    0.37
    水印
    0.37
    POSITIVE LOGITS
    Lub
    0.38
    㧔
    0.38
    라이
    0.37
    lub
    0.36
    Completed
    0.36
     ansch
    0.35
     beauté
    0.35
     beleza
    0.35
     ktorí
    0.35
    栓
    0.35
    Act Density 0.000%

    No Known Activations