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

    Neuronpedia

    INDEX
    Explanations

    US Political reservation complex ethical

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     सहारे
    0.42
    পারে
    0.40
     जनक
    0.40
    ﮧ
    0.40
    വിലെ
    0.39
    嘱
    0.39
    𝘆
    0.38
     fonbet
    0.37
     আশেপাশে
    0.37
    리스
    0.36
    POSITIVE LOGITS
     continuously
    0.43
     Am
    0.43
     AM
    0.40
     inline
    0.40
    öö
    0.39
    tei
    0.38
     am
    0.38
     straight
    0.38
     inwardly
    0.38
     amit
    0.38
    Act Density 0.002%

    No Known Activations