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

    Neuronpedia

    INDEX
    Explanations

    data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ade
    -0.07
    _CHOICES
    -0.06
     以
    -0.06
     افز
    -0.06
     μπορού
    -0.06
    706
    -0.06
    _VM
    -0.06
     Allocator
    -0.06
     한번
    -0.06
    ssql
    -0.06
    POSITIVE LOGITS
     사회
    0.07
    ,’”
    0.07
     MPS
    0.06
    ів
    0.06
    坛
    0.06
    mir
    0.06
     networking
    0.06
    가지
    0.06
     gestures
    0.06
    posium
    0.06
    Act Density 0.018%

    No Known Activations