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

    Neuronpedia

    INDEX
    Explanations

    store strings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    aceutical
    0.40
     subsidiaries
    0.38
    '
    0.38
     nur
    0.37
     Yeast
    0.37
    嗯
    0.37
    inaria
    0.37
     dreams
    0.36
     মর্যাদা
    0.36
     is
    0.36
    POSITIVE LOGITS
     ವಿದ
    0.52
    INTa
    0.49
    ˟
    0.48
    𝜁
    0.48
    𝑇
    0.48
     FILL
    0.47
    theta
    0.46
    ̟
    0.46
    𝐻
    0.46
    ದ್ದರಿಂದ
    0.46
    Act Density 0.002%

    No Known Activations