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

    Neuronpedia

    INDEX
    Explanations

    led

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    евой
    -0.06
     Loose
    -0.06
    红
    -0.06
     metaphor
    -0.06
    _vertical
    -0.06
    _configure
    -0.06
     pu
    -0.06
     incremental
    -0.06
     slut
    -0.06
    alance
    -0.06
    POSITIVE LOGITS
     puzzled
    0.11
     perplex
    0.10
     baff
    0.09
    _axes
    0.07
    ره
    0.07
     удив
    0.07
     educators
    0.07
     dismay
    0.07
     SCH
    0.07
    BX
    0.06
    Act Density 0.010%

    No Known Activations