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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (edge
    -0.07
     他
    -0.06
    .Subject
    -0.06
    	Grid
    -0.06
    PostExecute
    -0.06
     Roof
    -0.06
    Beth
    -0.06
    /thumb
    -0.06
    %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
    -0.06
    embr
    -0.06
    POSITIVE LOGITS
    COMM
    0.06
    regex
    0.06
     Shaun
    0.06
     Programme
    0.06
    -Clause
    0.06
    NV
    0.06
    CORE
    0.06
    uno
    0.06
    OTT
    0.06
     rif
    0.06
    Act Density 0.009%

    No Known Activations