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

    Neuronpedia

    INDEX
    Explanations

    ****I. Academics**Pro-EUSaintDidcontext managersoilbounty

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     desblo
    0.47
     rencontr
    0.43
     pres
    0.42
     espíritu
    0.41
     अंका
    0.39
     consecuencias
    0.39
     उत्साह
    0.39
     inmediato
    0.38
     فين
    0.38
     فرهنگی
    0.38
    POSITIVE LOGITS
     detached
    0.42
    did
    0.41
    GIN
    0.40
    Editors
    0.39
    attitude
    0.38
    Spec
    0.38
    Joel
    0.38
    脚
    0.38
    Did
    0.37
    detached
    0.37
    Act Density 0.001%

    No Known Activations