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

    Neuronpedia

    INDEX
    Explanations

    thing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    nel
    -0.08
    _MS
    -0.07
     spectra
    -0.07
    ewater
    -0.07
     Prec
    -0.07
     Brett
    -0.07
    ços
    -0.07
     poets
    -0.07
     Responses
    -0.07
    .broadcast
    -0.07
    POSITIVE LOGITS
     thing
    0.18
     Thing
    0.14
    Thing
    0.11
    thing
    0.08
    (thing
    0.07
     person
    0.07
     thinner
    0.06
    .Inner
    0.06
     Phrase
    0.06
    -chain
    0.06
    Act Density 0.013%

    No Known Activations