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

    Neuronpedia

    INDEX
    Explanations

    Jordi Cruz, Fideos Cremosos

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     locomotives
    0.45
    、​
    0.43
     newUser
    0.43
     پہا
    0.42
    फ्ते
    0.41
     escult
    0.40
     உலோக
    0.39
    Bubble
    0.39
     RESERVE
    0.38
    tolerant
    0.38
    POSITIVE LOGITS
     raid
    0.43
     loaf
    0.41
    4
    0.40
     тру
    0.40
    税务
    0.39
     byt
    0.39
     flour
    0.39
    Bread
    0.39
    业
    0.38
     Тру
    0.38
    Act Density 0.001%

    No Known Activations