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

    Neuronpedia

    INDEX
    Explanations

    conditional words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     villain
    -0.06
    .design
    -0.06
     digitalWrite
    -0.06
     год
    -0.06
    albums
    -0.06
    Movies
    -0.06
    ManyToOne
    -0.06
    írk
    -0.06
    IsNull
    -0.06
     esi
    -0.06
    POSITIVE LOGITS
    мет
    0.08
    Mag
    0.07
    (exit
    0.07
     Tanzania
    0.07
    _UPLOAD
    0.06
    isible
    0.06
    арь
    0.06
    ocup
    0.06
    ernity
    0.06
    MENTS
    0.06
    Act Density 0.057%

    No Known Activations