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

    Neuronpedia

    INDEX
    Explanations

    having, lift

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     motives
    0.63
     ballads
    0.63
    壕
    0.59
    riele
    0.58
     barriers
    0.58
     blanks
    0.57
    bins
    0.57
     valleys
    0.57
     effluents
    0.57
     Barriers
    0.57
    POSITIVE LOGITS
    Lift
    0.56
    lift
    0.52
     කො
    0.51
     लि
    0.50
    招生
    0.50
    зу
    0.50
    접
    0.50
     Nicht
    0.49
    สัน
    0.49
    locatorType
    0.49
    Act Density 0.001%

    No Known Activations