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

    Neuronpedia

    INDEX
    Explanations

    feature

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    láš
    -0.07
    чини
    -0.06
    View
    -0.06
    Clock
    -0.06
     Cleans
    -0.05
    zes
    -0.05
     publisher
    -0.05
    ابه
    -0.05
     Everybody
    -0.05
    integer
    -0.05
    POSITIVE LOGITS
     Fiesta
    0.07
     Hà
    0.07
     好
    0.07
    ereum
    0.07
     routines
    0.07
     강
    0.07
    ա�
    0.07
    .raw
    0.06
    去
    0.06
     yasak
    0.06
    Act Density 0.022%

    No Known Activations