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

    Neuronpedia

    INDEX
    Explanations

    urls containing /blog/

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ри
    0.99
    0.90
    ani
    0.83
    ä
    0.79
    ine
    0.79
    í
    0.75
     haven
    0.71
    ulation
    0.68
    raz
    0.66
     wash
    0.66
    POSITIVE LOGITS
    B
    1.05
    8
    1.05
    К
    1.03
    D
    0.98
    6
    0.96
    G
    0.95
    K
    0.94
    L
    0.92
    5
    0.91
    Ме
    0.89
    Act Density 0.004%

    No Known Activations