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

    Neuronpedia

    INDEX
    Explanations

    _length

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    、“
    -0.08
    ta
    -0.08
    sing
    -0.07
    em
    -0.07
     //<
    -0.07
    ots
    -0.07
     inline
    -0.07
    asse
    -0.07
    ets
    -0.07
    ais
    -0.07
    POSITIVE LOGITS
     постоян
    0.08
     процед
    0.08
    _PARSE
    0.08
     Wäh
    0.07
    ERRUPT
    0.07
    Occup
    0.07
    FORMATION
    0.07
     tranqu
    0.07
     HASH
    0.07
    umberland
    0.07
    Act Density 0.001%

    No Known Activations