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

    Neuronpedia

    INDEX
    Explanations

    methods, development, treatments

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    giatan
    -0.07
    фин
    -0.07
    بلغ
    -0.07
     Bürger
    -0.07
    ambi
    -0.07
    .hide
    -0.07
     WIDTH
    -0.06
    constructed
    -0.06
     Carnival
    -0.06
    estation
    -0.06
    POSITIVE LOGITS
     developmental
    0.07
     guys
    0.07
     [('
    0.07
    层级
    0.07
     salvation
    0.07
    置いて
    0.07
    쨓
    0.07
    了解一下
    0.07
     gearbox
    0.07
    rell
    0.07
    Act Density 0.118%

    No Known Activations