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

    Neuronpedia

    INDEX
    Explanations

    Let

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Case
    -0.07
     dejtingsaj
    -0.06
     уход
    -0.06
     Devil
    -0.06
    Dam
    -0.06
    ud
    -0.06
    ams
    -0.06
     hủy
    -0.06
     puzzle
    -0.06
    uss
    -0.05
    POSITIVE LOGITS
    κέ
    0.07
    žití
    0.06
    _person
    0.06
    .opt
    0.06
    invitation
    0.06
     technically
    0.06
    entanyl
    0.06
     nová
    0.06
     userdata
    0.06
     изображ
    0.06
    Act Density 0.013%

    No Known Activations