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

    Neuronpedia

    INDEX
    Explanations

    before

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    101
    -0.07
    FileName
    -0.06
     рук
    -0.06
     nud
    -0.06
    ęk
    -0.06
    �
    -0.06
    Typ
    -0.06
    841
    -0.06
     compound
    -0.06
     Insert
    -0.06
    POSITIVE LOGITS
    :UIControl
    0.06
    juries
    0.06
    #echo
    0.06
    (rng
    0.06
     emiss
    0.06
     опера
    0.06
    .isAdmin
    0.06
    .where
    0.06
     Terry
    0.06
     strt
    0.06
    Act Density 0.020%

    No Known Activations