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

    Neuronpedia

    INDEX
    Explanations

    connect you with resources

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    3
    0.70
     n
    0.66
    ים
    0.64
     share
    0.57
     investor
    0.56
     presentation
    0.56
     validator
    0.55
    t
    0.55
    IANA
    0.55
     get
    0.54
    POSITIVE LOGITS
     пациентов
    0.63
     лечение
    0.54
     pacientes
    0.54
    ğine
    0.52
    renergic
    0.52
     женщин
    0.52
    acariy
    0.52
    because
    0.51
    К
    0.51
    सी
    0.50
    Act Density 0.095%

    No Known Activations