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

    Neuronpedia

    INDEX
    Explanations

    talking to someone

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     loudest
    1.10
    Silence
    1.00
     heard
    0.98
     auditory
    0.98
    addresses
    0.98
     louder
    0.96
     chanted
    0.96
    哑
    0.96
    heard
    0.95
     voicemail
    0.95
    POSITIVE LOGITS
     दिखने
    0.98
     mắt
    0.93
    ség
    0.89
     wykon
    0.88
     alku
    0.87
     تجمع
    0.86
    位
    0.86
    te
    0.85
    নাত
    0.85
    ولي
    0.85
    Act Density 0.047%

    No Known Activations