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

    Neuronpedia

    INDEX
    Explanations

    ahead

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Theater
    -0.07
    _Location
    -0.06
     semanas
    -0.06
    umor
    -0.06
    Transition
    -0.06
    Restaurant
    -0.06
     Bakery
    -0.06
    _AdjustorThunk
    -0.06
     Proposal
    -0.06
     convers
    -0.06
    POSITIVE LOGITS
    ,double
    0.07
    (ed
    0.06
    ὰ
    0.06
    わけ
    0.06
    played
    0.06
    .clear
    0.06
    =result
    0.06
    (axis
    0.06
     discounted
    0.06
    (qu
    0.06
    Act Density 0.013%

    No Known Activations