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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hikes
    -0.06
     km
    -0.06
    >D
    -0.06
    conomic
    -0.06
    ’)
    -0.06
    ouched
    -0.06
    _'
    -0.06
     الع
    -0.06
    _"
    -0.06
    kids
    -0.06
    POSITIVE LOGITS
     twink
    0.07
    .BAD
    0.06
     SCM
    0.06
     Relative
    0.06
    ับปร
    0.06
    احی
    0.06
    _FRIEND
    0.06
    (Collectors
    0.06
    "]["
    0.06
    -urlencoded
    0.06
    Act Density 0.008%

    No Known Activations