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

    Neuronpedia

    INDEX
    Explanations

    add a quick

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     alleviated
    1.25
    sandbox
    1.20
    älfte
    1.17
    edores
    1.16
     mengapa
    1.16
    绎
    1.16
    oauth
    1.15
    milliseconds
    1.14
     disseminating
    1.13
    嗯
    1.13
    POSITIVE LOGITS
     $$\
    1.18
     conductance
    1.13
     Venus
    1.13
     $\$
    1.12
     Sauna
    1.09
     Operation
    1.07
     Gamma
    1.06
     fascia
    1.06
     pendant
    1.06
    Venus
    1.06
    Act Density 0.000%

    No Known Activations