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

    Neuronpedia

    INDEX
    Explanations

    introduces lists or explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    (
    0.47
    I
    0.45
    Ire
    0.41
    IS
    0.40
     Brist
    0.40
    Zeros
    0.40
    Y
    0.39
     Zentrum
    0.38
    Balls
    0.38
    ០០
    0.38
    POSITIVE LOGITS
    ين
    0.47
    ：
    0.47
     threaded
    0.44
     secuencia
    0.43
    ፦
    0.42
     conseguenza
    0.42
     chloroplast
    0.42
    ्वान
    0.42
    ācijas
    0.41
    ческая
    0.41
    Act Density 1.197%

    No Known Activations