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

    Neuronpedia

    INDEX
    Explanations

    IP

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    了一批
    -0.07
    ampie
    -0.07
    ৎ
    -0.07
    ✂
    -0.07
     manned
    -0.06
    證
    -0.06
     steals
    -0.06
     unanim
    -0.06
    iod
    -0.06
     bóng
    -0.06
    POSITIVE LOGITS
     verw
    0.07
     октября
    0.07
    .LabelControl
    0.07
    defer
    0.07
    _exe
    0.07
    Google
    0.07
    Doctrine
    0.07
    dług
    0.06
     artículo
    0.06
     antlr
    0.06
    Act Density 0.016%

    No Known Activations