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

    Neuronpedia

    INDEX
    Explanations

    mental states and processes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ث
    1.26
    in
    1.19
    on
    1.11
    غ
    1.07
    И
    1.06
    ال
    1.03
    ită
    1.00
    ி
    0.96
    i
    0.95
    الأ
    0.93
    POSITIVE LOGITS
    ;
    1.17
     mental
    0.95
     mentally
    0.88
     esprit
    0.85
     সারাদেশ
    0.81
     pona
    0.80
     dihar
    0.79
     homeschool
    0.79
     estern
    0.78
    ;}
    0.77
    Act Density 0.019%

    No Known Activations