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

    Neuronpedia

    INDEX
    Explanations

    are

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    columns
    -0.06
    -aligned
    -0.06
    implementation
    -0.06
     ifs
    -0.06
    .INVALID
    -0.06
    �除
    -0.05
     Buffett
    -0.05
     wield
    -0.05
    �i
    -0.05
    อาช
    -0.05
    POSITIVE LOGITS
     concatenated
    0.07
     histoire
    0.07
    습
    0.07
     설명
    0.06
    email
    0.06
    어
    0.06
    -decoration
    0.06
    енко
    0.06
    diff
    0.06
     cro
    0.06
    Act Density 0.001%

    No Known Activations