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

    Neuronpedia

    INDEX
    Explanations

    root cause

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     গণনা
    0.39
     কীর
    0.39
    ेशंस
    0.39
    Computing
    0.38
     خانو
    0.38
    abilität
    0.37
    展现
    0.37
    定义的
    0.37
     نگرانی
    0.37
    Jazz
    0.36
    POSITIVE LOGITS
     causes
    1.93
     penyebab
    1.78
    causes
    1.70
     causas
    1.69
     Causes
    1.68
    原因
    1.61
    Causes
    1.61
     причины
    1.55
    の原因
    1.49
     causative
    1.46
    Act Density 0.031%

    No Known Activations