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

    Neuronpedia

    INDEX
    Explanations

    Enthusiastic writing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _VLAN
    -0.06
     ------------
    -0.06
    juven
    -0.06
    an
    -0.06
    ança
    -0.06
    획
    -0.06
    žitě
    -0.06
     hứ
    -0.06
     pornofilm
    -0.06
    :"-
    -0.06
    POSITIVE LOGITS
     unreal
    0.07
    (frame
    0.06
    tlement
    0.06
    _friends
    0.06
     Firebase
    0.06
    .Failure
    0.05
    $",
    0.05
     Spurs
    0.05
     dataSource
    0.05
     федераль
    0.05
    Act Density 0.018%

    No Known Activations