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

    Neuronpedia

    INDEX
    Explanations

    Code syntax

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    numpy
    -0.07
    _para
    -0.06
     drift
    -0.06
    stral
    -0.06
     Astronomy
    -0.06
    (Data
    -0.06
     atr
    -0.06
    Think
    -0.06
    -byte
    -0.06
    .btnDelete
    -0.06
    POSITIVE LOGITS
     filmer
    0.07
     petits
    0.07
    assium
    0.06
     budeme
    0.06
     ListNode
    0.06
     rant
    0.06
     χρήση
    0.06
     muito
    0.06
     μπ
    0.06
    ,c
    0.06
    Act Density 0.021%

    No Known Activations