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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    FSIZE
    -0.07
    iant
    -0.07
    Це
    -0.07
    ॉर
    -0.07
    MORE
    -0.07
    --------------
    -0.06
    603
    -0.06
    ,self
    -0.06
     Likes
    -0.06
    ">

↵
    -0.06
    POSITIVE LOGITS
     DIC
    0.06
     Belgium
    0.06
     cooperation
    0.06
     대행
    0.06
    ']:
    0.06
     meaningful
    0.06
    _BOUNDS
    0.06
     meaning
    0.06
     Panama
    0.06
     ssl
    0.06
    Act Density 0.017%

    No Known Activations