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

    Neuronpedia

    INDEX
    Explanations

    must to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     quay
    -0.08
    PLIT
    -0.07
    MO
    -0.06
     hurting
    -0.06
    IDs
    -0.06
    _ca
    -0.06
     rx
    -0.06
     PCIe
    -0.06
    ňování
    -0.06
     spends
    -0.06
    POSITIVE LOGITS
     hairstyle
    0.06
     nä
    0.06
    Alan
    0.06
     inspiration
    0.06
     приход
    0.06
    mul
    0.06
     木
    0.06
    Bow
    0.06
    udev
    0.06
     również
    0.06
    Act Density 0.009%

    No Known Activations