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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ーパ
    -0.07
    [..
    -0.06
    prite
    -0.06
     Hor
    -0.06
    holm
    -0.06
    û
    -0.06
    ruh
    -0.06
     přísluš
    -0.06
    Gb
    -0.06
     Ply
    -0.06
    POSITIVE LOGITS
    “My
    0.07
    .block
    0.07
    needs
    0.07
    .Mouse
    0.07
     Sport
    0.06
    _COOKIE
    0.06
    .Enc
    0.06
    .sin
    0.06
     protr
    0.06
     Band
    0.06
    Act Density 0.022%

    No Known Activations