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

    Neuronpedia

    INDEX
    Explanations

    Formal/legal content

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     못
    -0.07
    pickle
    -0.06
    εται
    -0.06
     sesame
    -0.06
    ethoven
    -0.06
    =======
    -0.06
    Decoder
    -0.06
    }],
    -0.05
     sliced
    -0.05
    .io
    -0.05
    POSITIVE LOGITS
    //$
    0.07
    .:.:.:
    0.07
    ulance
    0.06
    观看
    0.06
    anst
    0.06
    grounds
    0.06
     Vulner
    0.06
    asiswa
    0.06
    �
    0.06
    Compet
    0.06
    Act Density 0.026%

    No Known Activations