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

    Neuronpedia

    INDEX
    Explanations

    python code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    8
    0.47
    h
    0.46
    ).
    0.46
     ۸
    0.43
     photore
    0.43
    :
    0.43
     tenis
    0.42
     HD
    0.42
     ).
    0.40
    v
    0.40
    POSITIVE LOGITS
    Lora
    0.49
    ISK
    0.49
     যাহ
    0.49
     झालेले
    0.49
    الل
    0.48
     اللَّ
    0.45
    LUT
    0.45
    <unused1112>
    0.44
     хорошие
    0.44
    ૃત
    0.43
    Act Density 0.038%

    No Known Activations