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

    Neuronpedia

    INDEX
    Explanations

    consequence or result

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     grinder
    0.72
    <%@
    0.72
    Plenty
    0.70
    igar
    0.70
    ivariable
    0.69
    ăzi
    0.68
    有很多
    0.67
     聞い
    0.66
    仔
    0.66
    ojo
    0.65
    POSITIVE LOGITS
     thus
    4.79
     thereby
    4.34
    thus
    4.12
    Thus
    3.86
     Thus
    3.81
     Таким
    3.51
     así
    3.49
     ainsi
    3.27
    从而
    3.26
    Таким
    3.20
    Act Density 0.069%

    No Known Activations