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

    Neuronpedia

    INDEX
    Explanations

    were

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Chris
    -0.07
    Chris
    -0.07
     JS
    -0.06
     x
    -0.06
    ,x
    -0.06
     Davis
    -0.06
    AH
    -0.06
     MAX
    -0.06
     Ross
    -0.06
     james
    -0.06
    POSITIVE LOGITS
    -le
    0.08
     wise
    0.07
    圭圭
    0.07
    lere
    0.07
     wandered
    0.07
    _SN
    0.07
    τρέ
    0.07
    _entropy
    0.07
     Meeting
    0.07
     borne
    0.07
    Act Density 0.051%

    No Known Activations