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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .SceneManagement
    -0.07
    _QU
    -0.06
    rient
    -0.06
    ')}↵
    -0.06
    (grid
    -0.06
    무
    -0.06
     smo
    -0.06
     Эти
    -0.06
     brunch
    -0.06
    _WRITE
    -0.06
    POSITIVE LOGITS
     свящ
    0.07
    CE
    0.06
    >d
    0.06
    -hero
    0.06
    ylland
    0.06
     slou
    0.06
     terminals
    0.06
    "|
    0.06
    (Parcel
    0.06
     nutshell
    0.06
    Act Density 0.063%

    No Known Activations