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

    Neuronpedia

    INDEX
    Explanations

    categories followed by lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     acquires
    0.41
     sl
    0.40
    NERS
    0.38
     kar
    0.36
     object
    0.36
     intends
    0.36
     vision
    0.35
     annoyance
    0.35
     tu
    0.35
     chl
    0.35
    POSITIVE LOGITS
    pecific
    0.70
     galore
    0.65
     आहेत
    0.63
    mith
    0.62
    cape
    0.62
    ales
    0.61
    ystem
    0.60
     are
    0.59
    pecies
    0.59
    ubmit
    0.59
    Act Density 0.065%

    No Known Activations