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

    Neuronpedia

    INDEX
    Explanations

    will

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    `↵
    -0.07
    Raise
    -0.07
     Iowa
    -0.07
    ером
    -0.07
     '">
    -0.07
    aaaa
    -0.07
    '])
    -0.06
     недели
    -0.06
    UT
    -0.06
    876
    -0.06
    POSITIVE LOGITS
     sürede
    0.07
    nick
    0.06
     grants
    0.06
     Bringing
    0.06
    _PACKAGE
    0.06
    ább
    0.06
     ortaya
    0.06
     İngilizce
    0.06
     permitting
    0.06
     至
    0.06
    Act Density 0.032%

    No Known Activations