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

    Neuronpedia

    INDEX
    Explanations

    Code events

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    '},
    -0.07
     COVID
    -0.06
     rau
    -0.06
     protagonist
    -0.06
     tantal
    -0.06
    songs
    -0.06
    .into
    -0.06
    י
    -0.06
    nage
    -0.06
     attitudes
    -0.06
    POSITIVE LOGITS
     aktivit
    0.07
    vim
    0.06
    PackageName
    0.06
     projector
    0.06
    .addColumn
    0.06
     dv
    0.06
     Alternative
    0.06
     fart
    0.06
     Clamp
    0.06
    оск
    0.06
    Act Density 0.014%

    No Known Activations