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

    Neuronpedia

    INDEX
    Explanations

    special

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _Out
    -0.07
     recourse
    -0.06
    //$
    -0.06
    foundland
    -0.06
    ierce
    -0.06
    vrd
    -0.06
    ذر
    -0.06
     scop
    -0.06
    ='../
    -0.06
     sempre
    -0.06
    POSITIVE LOGITS
     special
    0.08
     precious
    0.08
     disturbed
    0.07
     spirits
    0.07
     タ
    0.06
     transgender
    0.06
    bam
    0.06
    .j
    0.06
     rhe
    0.06
    .Cookie
    0.06
    Act Density 0.011%

    No Known Activations