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

    Neuronpedia

    INDEX
    Explanations

    core principles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ور
    0.75
    一個
    0.74
    ڈر
    0.73
    ت
    0.73
     fondamentale
    0.69
    к
    0.69
     первым
    0.68
    де
    0.66
     ears
    0.64
     jacks
    0.64
    POSITIVE LOGITS
    9
    0.93
    Cor
    0.76
    Core
    0.75
    s
    0.75
    7
    0.73
    iyor
    0.72
    8
    0.71
    Corr
    0.71
    em
    0.69
    3
    0.67
    Act Density 0.126%

    No Known Activations