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

    Neuronpedia

    INDEX
    Explanations

    Magento App PHP code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     as
    -0.84
    raine
    -0.82
    igar
    -0.74
    械
    -0.73
     gather
    -0.73
     ingest
    -0.72
     bianco
    -0.71
    驍
    -0.71
    OIR
    -0.71
    mesis
    -0.71
    POSITIVE LOGITS
     máte
    0.84
    閿
    0.82
     drenched
    0.81
     generell
    0.76
    inp
    0.76
     چنین
    0.76
     withered
    0.76
    沵
    0.75
    Miscellaneous
    0.74
    𝐇
    0.74
    Act Density 0.002%

    No Known Activations