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

    Neuronpedia

    INDEX
    Explanations

    Harmonics, messages, Aadhaar, responsibility, inactivated, deals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ین
    1.79
     bisschen
    1.63
    ير
    1.47
     creativo
    1.44
    Thats
    1.42
     miejscu
    1.38
    ج
    1.38
    да
    1.34
    ж
    1.34
    یک
    1.32
    POSITIVE LOGITS
    d
    2.38
    et
    2.16
    b
    2.11
    y
    2.08
    C
    2.08
    R
    1.91
    it
    1.89
    in
    1.86
    at
    1.84
    e
    1.84
    Act Density 0.000%

    No Known Activations