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

    Neuronpedia

    INDEX
    Explanations

    direction or position

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    manual
    -0.08
     docs
    -0.07
     Directed
    -0.06
    افر
    -0.06
     Asc
    -0.06
     dyn
    -0.06
     hx
    -0.06
    .gca
    -0.06
    Expr
    -0.06
     mainBundle
    -0.06
    POSITIVE LOGITS
    oriasis
    0.07
    研究
    0.07
     všem
    0.06
    βα
    0.06
     nouvelle
    0.06
     bamb
    0.06
    obile
    0.06
     overlooked
    0.06
     květ
    0.06
    ۲۸
    0.06
    Act Density 0.030%

    No Known Activations