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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _logical
    -0.07
    Replace
    -0.07
    	die
    -0.06
    Wei
    -0.06
     caut
    -0.06
     stavu
    -0.06
     nastav
    -0.06
    _TOGGLE
    -0.06
    Ci
    -0.06
     XM
    -0.06
    POSITIVE LOGITS
    _IMAGES
    0.06
     Samp
    0.06
     줄
    0.06
    balance
    0.06
    이슈
    0.06
    emean
    0.06
    ISTR
    0.06
     Britann
    0.06
     treasury
    0.06
    Inside
    0.06
    Act Density 0.003%

    No Known Activations