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

    Neuronpedia

    INDEX
    Explanations

    **B**alance, **L**oan, **P**ositions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     modulus
    0.39
    樵
    0.38
    သမ
    0.38
     relic
    0.37
     mixts
    0.36
    กีฬา
    0.36
     AVLNode
    0.35
    痺
    0.35
     centroid
    0.35
    ಬ್ಬಿಣ
    0.35
    POSITIVE LOGITS
    g
    0.42
    ando
    0.42
    ą
    0.41
    了
    0.38
    த்தை
    0.38
     T
    0.38
     Dutch
    0.36
    தியின்
    0.36
    ש
    0.36
    eda
    0.36
    Act Density 0.000%

    No Known Activations