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

    Neuronpedia

    INDEX
    Explanations

    Blend

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mole
    -0.08
    Rail
    -0.07
     voc
    -0.07
     FIG
    -0.07
     chica
    -0.07
    FIG
    -0.06
     rushes
    -0.06
     Cart
    -0.06
     foo
    -0.06
     rails
    -0.06
    POSITIVE LOGITS
     blend
    0.08
     blends
    0.08
    lanmış
    0.07
    .toolbox
    0.07
     Blend
    0.07
    nest
    0.06
    虫
    0.06
     Theodore
    0.06
     Variant
    0.06
    childs
    0.06
    Act Density 0.004%

    No Known Activations