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

    Neuronpedia

    INDEX
    Explanations

    there

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -svg
    -0.07
    .Euler
    -0.06
    Autom
    -0.06
    uck
    -0.06
    وقت
    -0.06
     кроме
    -0.06
     slips
    -0.06
    hx
    -0.06
     combust
    -0.06
    haps
    -0.06
    POSITIVE LOGITS
     there
    0.10
     There
    0.10
    “There
    0.08
     Ther
    0.08
     Hawaii
    0.08
    There
    0.08
    .de
    0.07
    Narr
    0.07
     Tar
    0.07
     دری
    0.07
    Act Density 0.019%

    No Known Activations