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

    Neuronpedia

    INDEX
    Explanations

    top 4

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    hdc
    0.37
    窸
    0.37
     motorised
    0.37
    ᕆ
    0.37
    <unused1063>
    0.37
     രംഗ
    0.37
    ॉर्क
    0.36
    ვი
    0.36
     الحلقه
    0.36
    DisplayStyle
    0.36
    POSITIVE LOGITS
     Valentina
    0.39
     NAG
    0.39
     Edison
    0.38
     B
    0.37
     nag
    0.36
    son
    0.35
     H
    0.35
     plan
    0.35
     GDPR
    0.35
     op
    0.35
    Act Density 0.000%

    No Known Activations