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

    Neuronpedia

    INDEX
    Explanations

    generate synthetic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    )+(
    0.44
    ahati
    0.39
    playlists
    0.39
    ansh
    0.39
    }<
    0.38
    guardian
    0.38
    strs
    0.38
     guardianship
    0.38
    }+(\
    0.38
     شدن
    0.37
    POSITIVE LOGITS
     (\%)
    0.41
     `%
    0.40
     individui
    0.38
     ಬೆ
    0.37
     lengthwise
    0.37
     včetně
    0.36
     (’
    0.36
     фено
    0.36
     Leng
    0.36
    㐄
    0.36
    Act Density 0.000%

    No Known Activations