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

    Neuronpedia

    INDEX
    Explanations

    comparisons and preferences

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    dağ
    -0.07
    -May
    -0.07
    PLACE
    -0.07
    ㅇ
    -0.07
    婠
    -0.07
    מוסר
    -0.07
    慎
    -0.06
     sip
    -0.06
    _bd
    -0.06
    镵
    -0.06
    POSITIVE LOGITS
    .alias
    0.07
     RID
    0.07
     Squadron
    0.07
     camper
    0.06
    _transfer
    0.06
     bush
    0.06
    .slot
    0.06
    onation
    0.06
     '(
    0.06
     }}">{{
    0.06
    Act Density 0.162%

    No Known Activations