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

    Neuronpedia

    INDEX
    Explanations

    that

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (orig
    -0.07
    zial
    -0.07
    _Real
    -0.07
     clash
    -0.07
    controls
    -0.07
    oria
    -0.06
     hostility
    -0.06
     guerr
    -0.06
     clashes
    -0.06
    ivot
    -0.06
    POSITIVE LOGITS
     Shannon
    0.07
     FVector
    0.06
     Marriage
    0.06
    樓
    0.06
     downloads
    0.06
    BAR
    0.06
     января
    0.06
    WI
    0.06
     För
    0.06
    .makedirs
    0.06
    Act Density 0.037%

    No Known Activations