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

    Neuronpedia

    INDEX
    Explanations

    weddings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sacked
    -0.07
    .drive
    -0.06
    .et
    -0.06
     archae
    -0.06
     rough
    -0.06
    .mkdirs
    -0.06
     Set
    -0.06
     occasional
    -0.06
     sire
    -0.06
     silly
    -0.06
    POSITIVE LOGITS
    _TMP
    0.06
    oru
    0.06
    níci
    0.06
    /kg
    0.06
     içeri
    0.06
    ESTAMP
    0.06
    ————————
    0.06
     rápido
    0.06
    onent
    0.06
    _balance
    0.06
    Act Density 0.011%

    No Known Activations