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

    Neuronpedia

    INDEX
    Explanations

    referring to specific terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ler
    0.45
    iler
    0.44
    otroph
    0.44
    𝐫
    0.43
    cash
    0.43
    oubt
    0.43
    स्थापन
    0.42
    ka
    0.42
    ᴋ
    0.42
    ylon
    0.41
    POSITIVE LOGITS
    0.57
     sabbatical
    0.50
     around
    0.49
     ,"
    0.44
     ID
    0.44
     LIB
    0.44
     entr
    0.43
     CD
    0.41
     IB
    0.41
    ))){
    0.41
    Act Density 0.000%

    No Known Activations