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

    Neuronpedia

    INDEX
    Explanations

    Numbers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    umped
    -0.08
     impressions
    -0.07
    Perform
    -0.07
     hid
    -0.07
    quil
    -0.07
     astronomical
    -0.06
    _header
    -0.06
    iale
    -0.06
    Nos
    -0.06
    .setDescription
    -0.06
    POSITIVE LOGITS
    _bug
    0.07
    	ms
    0.07
     faaliyet
    0.06
     vu
    0.06
    /books
    0.06
    _MPI
    0.06
     زیاد
    0.06
     घटन
    0.06
    nodiscard
    0.06
    eor
    0.06
    Act Density 0.010%

    No Known Activations