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

    Neuronpedia

    INDEX
    Explanations

    aiming for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     должна
    0.47
    нда
    0.46
     должен
    0.46
    atilde
    0.45
    ？”
    0.44
    asakan
    0.44
    емся
    0.43
    νοντας
    0.43
    ună
    0.42
    ઞ
    0.42
    POSITIVE LOGITS
     recob
    0.45
     preced
    0.44
     reflet
    0.44
     compassion
    0.44
     cases
    0.43
     başlayalım
    0.43
     supportive
    0.43
     pathogenesis
    0.43
     neutral
    0.42
    াসেব
    0.42
    Act Density 0.001%

    No Known Activations