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

    Neuronpedia

    INDEX
    Explanations

    code structure with colon

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     رشد
    0.44
     इद
    0.43
    lichting
    0.40
    வுகள்
    0.39
     إذا
    0.39
    }$;
    0.38
    вість
    0.38
    !";
    0.38
    ك
    0.38
    टेज
    0.38
    POSITIVE LOGITS
     Regist
    0.39
     associates
    0.38
     principales
    0.38
     requires
    0.38
     GmbH
    0.38
     principaux
    0.37
    :
    0.37
     two
    0.36
    EXTRA
    0.36
     maintaining
    0.36
    Act Density 0.030%

    No Known Activations