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

    Neuronpedia

    INDEX
    Explanations

    cooking heat instructions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .”
    0.61
    ();
    0.54
     n
    0.52
    .<
    0.51
     .”
    0.51
    .’
    0.48
     AIAA
    0.47
     viele
    0.46
     Internal
    0.46
     Babb
    0.46
    POSITIVE LOGITS
    ुरु
    0.52
    趼
    0.51
    위
    0.50
    妧
    0.50
    toMap
    0.49
    鵲
    0.49
    悳
    0.48
     relacion
    0.47
    あなたの
    0.47
    рабаты
    0.47
    Act Density 0.007%

    No Known Activations