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

    Neuronpedia

    INDEX
    Explanations

    dat

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     *"
    -0.07
     revive
    -0.06
    Argentina
    -0.06
     adrenaline
    -0.06
     torn
    -0.06
    #c
    -0.06
     RIP
    -0.06
    ている
    -0.06
    :I
    -0.06
     dma
    -0.06
    POSITIVE LOGITS
     DAT
    0.07
     Observatory
    0.07
    aut
    0.07
    AT
    0.07
    vat
    0.07
    Nat
    0.07
     localVar
    0.07
     accept
    0.07
     thức
    0.07
    特
    0.07
    Act Density 0.007%

    No Known Activations