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

    Neuronpedia

    INDEX
    Explanations

    written text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ่าย
    -0.08
     बस
    -0.07
    quality
    -0.07
    .norm
    -0.07
    pecting
    -0.06
     defensively
    -0.06
    ourcem
    -0.06
     everything
    -0.06
    れど
    -0.06
    -direct
    -0.06
    POSITIVE LOGITS
    _contin
    0.08
     ofrece
    0.06
     wykon
    0.06
    ollapsed
    0.06
     resin
    0.06
     گرد
    0.06
    -spec
    0.06
    _text
    0.06
    サー
    0.06
     Disp
    0.06
    Act Density 0.106%

    No Known Activations