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

    Neuronpedia

    INDEX
    Explanations

    template

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .setX
    -0.07
     wnd
    -0.07
    +(\
    -0.07
    _TAG
    -0.07
     kök
    -0.07
     leží
    -0.07
    isbn
    -0.06
     bietet
    -0.06
     Netz
    -0.06
    Misc
    -0.06
    POSITIVE LOGITS
     apologies
    0.07
     fatal
    0.06
     Others
    0.06
     json
    0.06
    905
    0.06
    andard
    0.06
     magma
    0.06
    ilha
    0.06
     Timber
    0.06
    _codes
    0.06
    Act Density 0.001%

    No Known Activations