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

    Neuronpedia

    INDEX
    Explanations

    foundational knowledge

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     R
    0.37
    所以
    0.36
     SO
    0.36
    Macro
    0.35
     Unreal
    0.35
     pena
    0.35
     Mobi
    0.35
    现
    0.35
    输出
    0.34
    카오
    0.34
    POSITIVE LOGITS
    ímav
    0.41
    <unused2026>
    0.39
     accompanied
    0.39
    éon
    0.38
    yrıca
    0.37
     όμως
    0.37
     piante
    0.37
     φωτο
    0.37
     புகைப்பட
    0.37
     acompañado
    0.36
    Act Density 1.093%

    No Known Activations