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

    Neuronpedia

    INDEX
    Explanations

    un

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     p
    -0.06
    	C
    -0.06
     cor
    -0.06
     additional
    -0.06
     Have
    -0.06
     House
    -0.06
    takes
    -0.06
     improvements
    -0.06
     though
    -0.06
     гід
    -0.06
    POSITIVE LOGITS
    MethodImpl
    0.07
    UNS
    0.07
     <=>
    0.07
    .Weight
    0.07
     ανα
    0.07
    _pdu
    0.07
    olian
    0.06
     Prahy
    0.06
    ])/
    0.06
     slun
    0.06
    Act Density 0.011%

    No Known Activations