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

    Neuronpedia

    INDEX
    Explanations

    words starting with mar

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𒅴
    0.36
    SLASH
    0.33
    ብስብ
    0.32
    hemia
    0.31
    relativePath
    0.31
    )'=='
    0.31
     closeModal
    0.31
     trimethyl
    0.31
    隹
    0.31
    infodisc
    0.30
    POSITIVE LOGITS
    Mar
    3.22
     MAR
    3.16
     mar
    3.03
    MAR
    3.03
     مار
    3.03
    mar
    2.94
     Mar
    2.92
     мар
    2.92
     Мар
    2.72
    مار
    2.61
    Act Density 0.100%

    No Known Activations