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

    Neuronpedia

    INDEX
    Explanations

    Code or technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Maxim
    -0.07
     ostat
    -0.07
     Gra
    -0.07
     Loài
    -0.07
     Sergio
    -0.07
     тогда
    -0.07
     undermin
    -0.06
     began
    -0.06
     DefaultValue
    -0.06
    aggregate
    -0.06
    POSITIVE LOGITS
    nels
    0.06
    δρο
    0.06
     :.:
    0.06
     Japon
    0.06
     προϊ
    0.06
     PAD
    0.06
     состоянии
    0.06
     verses
    0.06
    uvian
    0.06
    93
    0.06
    Act Density 0.094%

    No Known Activations