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

    Neuronpedia

    INDEX
    Explanations

    boolean true/false

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Comfort
    0.43
     Castle
    0.42
     Samaritan
    0.40
     relays
    0.39
     Merlot
    0.39
    copyOf
    0.39
     Prev
    0.38
     Copies
    0.38
    ++,
    0.38
     duplicates
    0.37
    POSITIVE LOGITS
     pell
    0.41
    HEX
    0.37
    ग्
    0.37
    ਧੀ
    0.36
     Mies
    0.36
     আনা
    0.36
    EJ
    0.35
     wichtige
    0.35
    ᓇ
    0.35
    Imagem
    0.35
    Act Density 0.000%

    No Known Activations