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

    Neuronpedia

    INDEX
    Explanations

    solve a problem

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ὠ
    1.05
     fortement
    1.00
    ON
    0.98
     пера
    0.91
    ә
    0.91
    이나
    0.90
    п
    0.89
    ﻃ
    0.89
    させる
    0.88
    ъ
    0.88
    POSITIVE LOGITS
     problemas
    1.07
     problemi
    1.07
     Probleme
    1.05
     disparities
    1.04
     adversity
    1.02
     problems
    1.02
    issues
    1.02
     PROBLEMS
    1.02
    钅
    1.02
    ⌄
    1.02
    Act Density 0.556%

    No Known Activations