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

    Neuronpedia

    INDEX
    Explanations

    explicit sexual content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     standardised
    0.49
     underpin
    0.48
     putative
    0.48
     அடிப்படையில்
    0.47
     actualizada
    0.47
     substantive
    0.47
     hinsichtlich
    0.46
     simplify
    0.46
     adapta
    0.46
     সেক্ষেত্রে
    0.46
    POSITIVE LOGITS
     glistening
    0.94
     lust
    0.87
     merciless
    0.84
     drenched
    0.84
     sickly
    0.84
     trembling
    0.84
     lifeless
    0.84
     disgusting
    0.82
     sickening
    0.82
     excruciating
    0.81
    Act Density 0.108%

    No Known Activations