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

    Neuronpedia

    INDEX
    Explanations

    )

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ﺕ
    -0.07
     District
    -0.07
    公网安
    -0.07
    vron
    -0.07
    **(
    -0.06
    	NullCheck
    -0.06
    つもり
    -0.06
     Jill
    -0.06
    ˋ
    -0.06
     Detective
    -0.06
    POSITIVE LOGITS
    _keeper
    0.08
     backups
    0.08
    _bounds
    0.07
    _OP
    0.07
    (radius
    0.07
    	rep
    0.07
    -------↵
    0.07
    ケア
    0.07
     пом
    0.07
    (cube
    0.06
    Act Density 0.021%

    No Known Activations