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

    Neuronpedia

    INDEX
    Explanations

    refer, understand why, others on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Matemática
    0.49
     auriculares
    0.49
     ramen
    0.48
     áreas
    0.48
     wszyst
    0.45
     hopper
    0.45
     Ramen
    0.43
     rbuf
    0.43
    ಾಗಿತ್ತು
    0.43
     diagonally
    0.43
    POSITIVE LOGITS
    k
    0.52
    st
    0.47
    ﻙ
    0.47
    PSK
    0.45
    Magnitude
    0.45
    சி
    0.43
    c
    0.43
    K
    0.43
    ASA
    0.42
    Recursive
    0.42
    Act Density 0.000%

    No Known Activations