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

    Neuronpedia

    INDEX
    Explanations

    ;

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     binary
    -0.07
     Tor
    -0.06
     cena
    -0.06
     خر
    -0.06
    高度
    -0.06
     sine
    -0.06
    steam
    -0.06
     Tops
    -0.06
     Counter
    -0.06
    _room
    -0.06
    POSITIVE LOGITS
     snap
    0.07
    Considering
    0.07
    ()].
    0.07
    ayla
    0.06
     завд
    0.06
     deselect
    0.06
    .showMessageDialog
    0.06
    说话
    0.06
     restau
    0.06
     Δε
    0.06
    Act Density 0.001%

    No Known Activations