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

    Neuronpedia

    INDEX
    Explanations

    OSHA requirements, navigate daily

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    schule
    0.50
     blink
    0.49
    es
    0.48
     blinking
    0.46
     align
    0.45
     automatisch
    0.45
    পৌ
    0.44
    pipe
    0.43
    quick
    0.43
     addons
    0.42
    POSITIVE LOGITS
    脂肪
    0.45
    )....
    0.45
    瑚
    0.45
    တစ်
    0.44
    वेत
    0.44
    珽
    0.44
    뵈
    0.44
    ཎ
    0.43
    琊
    0.43
    говари
    0.42
    Act Density 0.033%

    No Known Activations