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

    Neuronpedia

    INDEX
    Explanations

    historical citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Fabi
    0.42
    号码
    0.41
     Aussie
    0.41
     člov
    0.40
     વધારે
    0.40
    发出
    0.38
    莳
    0.38
     количе
    0.38
    咆
    0.38
     абсолютно
    0.37
    POSITIVE LOGITS
     historian
    0.44
    Template
    0.38
     historians
    0.38
    cite
    0.37
    "]}
    0.36
     airfield
    0.36
    ^
    0.36
     gesch
    0.36
    eret
    0.35
    <sup>
    0.35
    Act Density 0.000%

    No Known Activations