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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ình
    -0.06
    Though
    -0.06
    한다
    -0.06
     fin
    -0.06
    +i
    -0.06
     ideally
    -0.06
    Next
    -0.06
    Few
    -0.06
     badly
    -0.06
    enuous
    -0.06
    POSITIVE LOGITS
     filtering
    0.08
    <source
    0.07
    ині
    0.06
    chandle
    0.06
     concurrency
    0.06
    ptive
    0.06
     Sussex
    0.06
    reg
    0.06
     person
    0.06
    ันก
    0.06
    Act Density 0.229%

    No Known Activations