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

    Neuronpedia

    INDEX
    Explanations

    mathematical conjectures and proofs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     assumptive
    0.52
    uptime
    0.49
    рсә
    0.47
     hoodies
    0.46
    वत्ता
    0.46
    舆
    0.46
    নাকে
    0.45
    nmea
    0.45
     lawfully
    0.44
    जारत
    0.44
    POSITIVE LOGITS
     theorems
    1.06
     Theorems
    1.00
     theorem
    0.97
     Theorem
    0.93
    Theorem
    0.91
     conjectured
    0.87
     conjectures
    0.83
     generalizations
    0.82
     conjecture
    0.79
     Conjecture
    0.78
    Act Density 0.026%

    No Known Activations