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

    Neuronpedia

    INDEX
    Explanations

    's

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Liabilities
    0.57
    Observers
    0.56
     Poincaré
    0.55
    電荷
    0.55
    0.52
    nicheskij
    0.51
    🩹
    0.51
    <bbox>
    0.50
    ⇵
    0.50
     quadrado
    0.50
    POSITIVE LOGITS
     minim
    0.52
    st
    0.49
     sync
    0.49
     comple
    0.49
     apr
    0.49
     conform
    0.46
     base
    0.46
     monolith
    0.46
     condu
    0.46
     savoir
    0.46
    Act Density 0.000%

    No Known Activations