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

    Neuronpedia

    INDEX
    Explanations

    Frequency

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (pre
    -0.07
     fixes
    -0.07
    -phone
    -0.07
     Booth
    -0.06
    @implementation
    -0.06
    /var
    -0.06
     Kennedy
    -0.06
    Buttons
    -0.06
    "}>↵
    -0.06
     cạnh
    -0.06
    POSITIVE LOGITS
    GF
    0.06
    igated
    0.06
     textAlign
    0.06
    险
    0.06
     crystals
    0.06
    砂
    0.06
     Rin
    0.06
    lace
    0.06
    RY
    0.06
    illum
    0.06
    Act Density 0.017%

    No Known Activations