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

    Neuronpedia

    INDEX
    Explanations

    complex nuanced approach

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Oak
    0.38
    ლე
    0.38
    樟
    0.37
     வந்த
    0.36
    愉快
    0.36
     Acosta
    0.36
    strasse
    0.36
     விளையாட்டு
    0.36
    createNew
    0.35
    茶叶
    0.35
    POSITIVE LOGITS
    either
    0.38
     அவரின்
    0.37
     either
    0.37
     резо
    0.37
    ubei
    0.36
     cubre
    0.36
     restar
    0.36
     Scream
    0.35
    χει
    0.35
     responder
    0.35
    Act Density 0.004%

    No Known Activations