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

    Neuronpedia

    INDEX
    Explanations

    mathematical proofs and theorems

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    蝠
    0.59
    j
    0.57
     Loew
    0.57
     northeast
    0.57
    “
    0.55
     castles
    0.54
    वाट
    0.54
    噉
    0.54
    ま
    0.54
    ka
    0.53
    POSITIVE LOGITS
    انيا
    0.61
     theorem
    0.57
     theorems
    0.57
    Theorem
    0.56
    Topology
    0.56
    크
    0.55
    isometric
    0.55
     있다
    0.53
     ovog
    0.53
    ופה
    0.53
    Act Density 0.044%

    No Known Activations