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

    Neuronpedia

    INDEX
    Explanations

    foreign key constraints and values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     الز
    0.46
     ਜ਼
    0.46
    PosZ
    0.42
     Zane
    0.41
     ziff
    0.40
    𝘻
    0.40
     závod
    0.40
    輾
    0.39
     zove
    0.39
    ᴢ
    0.39
    POSITIVE LOGITS
     Sen
    0.41
     exquis
    0.40
     premio
    0.39
     ne
    0.38
     reference
    0.36
     exert
    0.36
    nl
    0.36
     fox
    0.36
     Speicher
    0.35
     target
    0.35
    Act Density 0.000%

    No Known Activations