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

    Neuronpedia

    INDEX
    Explanations

    specific questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    gallon
    0.46
     Dynamics
    0.45
    মেল
    0.44
     broadcast
    0.43
     nCurrent
    0.43
     parameter
    0.42
    藥
    0.42
    2
    0.42
    醇
    0.40
     FEDERAL
    0.40
    POSITIVE LOGITS
    getBlue
    0.53
    জে
    0.48
    해야
    0.46
    рет
    0.45
     اللي
    0.44
    getData
    0.44
     позна
    0.44
     पुष्टि
    0.44
    abca
    0.43
     дете
    0.43
    Act Density 0.001%

    No Known Activations