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

    Neuronpedia

    INDEX
    Explanations

    colon

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    posite
    -0.08
     Noticed
    -0.07
    resolved
    -0.07
    Terrain
    -0.07
     cognitive
    -0.07
    .Diagnostics
    -0.06
    Coding
    -0.06
     tgt
    -0.06
     sed
    -0.06
     Logan
    -0.06
    POSITIVE LOGITS
    +",
    0.06
    _END
    0.06
    面议
    0.06
     declares
    0.06
    늘
    0.06
     Barbie
    0.06
     ΠΡ
    0.06
     waterfall
    0.06
    xCF
    0.06
     '';
    0.05
    Act Density 0.012%

    No Known Activations