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

    Neuronpedia

    INDEX
    Explanations

    legal revocations/violations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    xee
    -0.07
    䂮
    -0.07
     refuge
    -0.07
    getStore
    -0.07
     Cop
    -0.06
    intptr
    -0.06
     바랍
    -0.06
    }{↵
    -0.06
    济
    -0.06
    (area
    -0.06
    POSITIVE LOGITS
     feel
    0.07
     promotes
    0.06
     conn
    0.06
    租赁
    0.06
    几个人
    0.06
    ened
    0.06
     lined
    0.06
    IG
    0.06
    EMENT
    0.06
     conjunto
    0.06
    Act Density 0.007%

    No Known Activations