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

    Neuronpedia

    INDEX
    Explanations

    languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    he
    0.69
    ant
    0.67
    re
    0.63
    ere
    0.62
    ea
    0.62
    е
    0.61
    anci
    0.60
    er
    0.58
    hare
    0.57
    ime
    0.57
    POSITIVE LOGITS
     Languages
    1.39
     languages
    1.38
    languages
    1.35
     Gould
    1.33
     Sprachen
    1.32
     líng
    1.31
     fundraisers
    1.31
     Roth
    1.29
    Roth
    1.29
     Typography
    1.24
    Act Density 0.802%

    No Known Activations