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

    Neuronpedia

    INDEX
    Explanations

    license/certification numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ằ
    -0.07
     życ
    -0.06
     �
    -0.06
    victim
    -0.06
     jerk
    -0.06
    �
    -0.06
    %^
    -0.06
    ίνη
    -0.06
    ンバ
    -0.06
     counts
    -0.06
    POSITIVE LOGITS
     suspend
    0.07
    Ent
    0.07
    خص
    0.07
    Element
    0.07
     accred
    0.07
     kinds
    0.07
     beach
    0.06
    .access
    0.06
    aru
    0.06
    σπ
    0.06
    Act Density 0.002%

    No Known Activations