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

    Neuronpedia

    INDEX
    Explanations

    funding rounds Series A B

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     aloud
    0.43
     cheery
    0.41
     prickly
    0.41
     inquisitive
    0.40
     instructor
    0.40
     enigmatic
    0.40
     Instant
    0.39
     Instruct
    0.39
     eccentric
    0.39
     peculiar
    0.39
    POSITIVE LOGITS
    GA
    0.31
    ढ़ाई
    0.30
     перева
    0.30
     बढ़
    0.30
    äden
    0.30
     heaven
    0.30
    issé
    0.30
    adihi
    0.30
     চলতি
    0.30
    protect
    0.29
    Act Density 0.003%

    No Known Activations