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

    Neuronpedia

    INDEX
    Explanations

    void

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _WATCH
    -0.07
    ungeon
    -0.07
    _LEAVE
    -0.07
    detach
    -0.06
    =:
    -0.06
    errar
    -0.06
    rawer
    -0.06
    _helpers
    -0.06
    (QtCore
    -0.06
    策
    -0.06
    POSITIVE LOGITS
    duct
    0.06
    sects
    0.06
    )."
    0.06
    ्षण
    0.06
     Clip
    0.06
     стро
    0.06
    扎
    0.05
     blanks
    0.05
    ="#">↵
    0.05
    ОР
    0.05
    Act Density 0.001%

    No Known Activations