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

    Neuronpedia

    INDEX
    Explanations

    formal, professional, patronage, engaging

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    lights
    0.42
    formance
    0.41
    shapes
    0.41
    ained
    0.41
    space
    0.41
    anch
    0.40
    presentation
    0.39
    properties
    0.38
    wal
    0.38
    transforms
    0.38
    POSITIVE LOGITS
     GDP
    0.41
    estro
    0.41
     സാധ്യത
    0.39
    紳
    0.39
    umlu
    0.38
    Free
    0.38
    FREE
    0.38
    BSD
    0.38
    Bruce
    0.38
    흘
    0.38
    Act Density 0.000%

    No Known Activations