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

    Neuronpedia

    INDEX
    Explanations

    written texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ())↵↵
    -0.07
     Examples
    -0.07
    ([(
    -0.06
    �
    -0.06
    Jac
    -0.06
    步
    -0.06
    另外
    -0.06
    -(
    -0.06
    (inflater
    -0.06
    (sn
    -0.06
    POSITIVE LOGITS
     sal
    0.07
    ails
    0.07
     양
    0.07
    owner
    0.07
     Wait
    0.07
     Ανα
    0.07
     독일
    0.07
     Brewers
    0.06
    rest
    0.06
    _bar
    0.06
    Act Density 0.000%

    No Known Activations