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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    depth
    -0.07
    etics
    -0.07
     XM
    -0.07
    elps
    -0.06
    irates
    -0.06
    ocre
    -0.06
    てる
    -0.06
     [
    -0.06
    ظˆط
    -0.06
    adelphia
    -0.06
    POSITIVE LOGITS
    }-
    0.07
    (std
    0.06
     Configuration
    0.06
    (const
    0.06
     founder
    0.06
    flags
    0.06
     violate
    0.06
     αυτή
    0.06
    ном
    0.06
    :</
    0.06
    Act Density 0.040%

    No Known Activations