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

    Neuronpedia

    INDEX
    Explanations

    budgets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     polite
    -0.07
    	parser
    -0.07
     excit
    -0.07
     της
    -0.07
    .newaxis
    -0.07
     axial
    -0.07
    Tambah
    -0.07
    avadoc
    -0.06
     oc
    -0.06
    Anything
    -0.06
    POSITIVE LOGITS
    quipe
    0.07
    .Ship
    0.06
    elow
    0.06
    /ph
    0.06
    .bot
    0.06
    _UINT
    0.06
     Nhật
    0.06
     scrim
    0.06
     Loot
    0.06
    .В
    0.06
    Act Density 0.030%

    No Known Activations