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

    Neuronpedia

    INDEX
    Explanations

    offering further assistance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    newUser
    0.32
     многочис
    0.30
    注重
    0.30
    重视
    0.29
    Emily
    0.28
    ESD
    0.28
    issen
    0.28
    eyn
    0.27
    發生
    0.27
    மின்
    0.27
    POSITIVE LOGITS
     तरीका
    0.57
     ways
    0.55
     anything
    0.54
     maneira
    0.52
     manera
    0.51
     cách
    0.51
     specific
    0.51
     način
    0.51
     way
    0.50
     façons
    0.49
    Act Density 0.015%

    No Known Activations