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

    Neuronpedia

    INDEX
    Explanations

    Acronyms/Abbreviations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ç¬ij声
    -0.25
     kiá»ĩn
    -0.25
     nues
    -0.24
    ismatic
    -0.24
    Debe
    -0.24
    èĨĢ
    -0.24
    _Cell
    -0.24
    thren
    -0.23
    áºŃy
    -0.23
    ä»»
    -0.23
    POSITIVE LOGITS
    æī§è¡Į
    0.32
    thag
    0.30
    GP
    0.28
    大åѦ
    0.28
    si
    0.28
    强åĮĸ
    0.27
     Final
    0.27
    ä¼ĺè¶Ĭ
    0.26
    fy
    0.26
    çī¹æ®Ĭ
    0.26
    Act Density 0.012%

    No Known Activations