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

    Neuronpedia

    INDEX
    Explanations

    system commands and output

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ริ
    1.43
    ない
    1.43
    ren
    1.35
    מיד
    1.30
    mi
    1.28
     തന്നെ
    1.26
    renz
    1.24
    uct
    1.23
     affidavit
    1.22
    ↪
    1.22
    POSITIVE LOGITS
     depriving
    1.40
    一定的
    1.36
     particulares
    1.36
     distintas
    1.36
    Благо
    1.35
     delitos
    1.34
    ţi
    1.33
    ﾞ
    1.32
     gênero
    1.32
    可以让
    1.31
    Act Density 0.006%

    No Known Activations