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

    Neuronpedia

    INDEX
    Explanations

    required conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <unused2020>
    0.38
    anness
    0.37
    rightsquigarrow
    0.36
     unmittelbar
    0.36
    glicherweise
    0.36
    త్‌
    0.36
     거고
    0.35
    ጐ
    0.35
    ≥
    0.35
    理解
    0.35
    POSITIVE LOGITS
     are
    0.47
     de
    0.46
     saya
    0.45
     you
    0.45
    !");
    0.45
     is
    0.44
     to
    0.43
     of
    0.42
     fue
    0.42
    !",
    0.42
    Act Density 0.026%

    No Known Activations