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

    Neuronpedia

    INDEX
    Explanations

    4chan greentexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    1
    0.59
     Пример
    0.55
     सामान्य
    0.53
     means
    0.52
    ोड
    0.52
    barg
    0.52
    Fg
    0.52
     அதே
    0.51
    ry
    0.50
    gt
    0.50
    POSITIVE LOGITS
    erler
    0.62
     langage
    0.59
    };
    0.55
     moeilijk
    0.55
    諰
    0.54
     linguaggio
    0.52
    人們
    0.51
    逹
    0.51
    难以
    0.50
    搆
    0.49
    Act Density 0.001%

    No Known Activations