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

    Neuronpedia

    INDEX
    Explanations

    table separators | and similar

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    चुअल
    0.36
    atthena
    0.35
    ukiyoe
    0.34
    apayati
    0.33
    Điều
    0.33
     ludzie
    0.33
    ógł
    0.32
    avacanam
    0.32
    uhà
    0.32
    goài
    0.32
    POSITIVE LOGITS
    ↵
    0.35
     D
    0.32
     De
    0.32
     V
    0.32
     ARE
    0.32
    0.32
     IS
    0.31
     C
    0.31
     N
    0.31
     I
    0.31
    Act Density 0.170%

    No Known Activations