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

    Neuronpedia

    INDEX
    Explanations

    muladhara, indradhanush, bhargava

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     செல்சிய
    0.41
     回
    0.40
    荩
    0.38
    asting
    0.38
    flower
    0.38
    Helpers
    0.38
    Hector
    0.38
    мого
    0.37
    AVLNode
    0.37
    ܡ
    0.37
    POSITIVE LOGITS
    waj
    0.59
     vaj
    0.43
    वाज
    0.41
     dwell
    0.40
     way
    0.38
     trial
    0.38
    vaj
    0.38
     organs
    0.38
     DW
    0.38
     strides
    0.37
    Act Density 0.002%

    No Known Activations