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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kök
    -0.07
    ndef
    -0.07
     DECL
    -0.07
     explorer
    -0.06
    _elems
    -0.06
     opened
    -0.06
    uncan
    -0.06
    tbody
    -0.06
     nationalists
    -0.06
    旦
    -0.06
    POSITIVE LOGITS
     док
    0.07
    ()+"
    0.07
     generado
    0.07
    +(
    0.06
     upbeat
    0.06
     (~
    0.06
    elfare
    0.06
    63
    0.06
    china
    0.06
    !",
    0.06
    Act Density 0.002%

    No Known Activations