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

    Neuronpedia

    INDEX
    Explanations

    say ASSERT

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ._↵
    -0.07
    Face
    -0.06
     PARAMETERS
    -0.06
    ům
    -0.06
    ,),↵
    -0.06
    .Screen
    -0.06
    >)↵
    -0.06
    (NUM
    -0.06
    (em
    -0.06
    .*;↵↵
    -0.06
    POSITIVE LOGITS
     नजर
    0.07
    posting
    0.07
     مقابل
    0.07
     overl
    0.06
     �
    0.06
    仲
    0.06
    ินทร
    0.06
     jumped
    0.06
     즉
    0.06
    iment
    0.06
    Act Density 0.005%

    No Known Activations