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

    Neuronpedia

    INDEX
    Explanations

    Scientific research papers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    原始内容存档于
    -0.56
     quitté
    -0.56
    OGND
    -0.54
    ValueStyle
    -0.54
    tagext
    -0.52
     actuels
    -0.49
     refusé
    -0.48
     fermés
    -0.47
     apparaître
    -0.47
    abestanden
    -0.45
    POSITIVE LOGITS
     calendriers
    0.60
     Madura
    0.60
     PARSER
    0.57
     везе
    0.54
     GLC
    0.54
     necks
    0.52
     Disposition
    0.51
     clamp
    0.51
     ujednoznacz
    0.50
    WAUKEE
    0.49
    Act Density 0.021%

    No Known Activations