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

    Neuronpedia

    INDEX
    Explanations

    pondering big questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     forne
    0.43
     costes
    0.43
     heur
    0.42
     Largest
    0.42
     fatores
    0.40
     dobre
    0.40
     kwal
    0.40
     delas
    0.40
     அம்ம
    0.39
     Neighbour
    0.39
    POSITIVE LOGITS
    vert
    0.51
    kreuz
    0.48
    estomac
    0.46
    instruction
    0.46
    edited
    0.46
    account
    0.45
    preds
    0.45
    氈
    0.45
    animal
    0.45
    Jahr
    0.44
    Act Density 0.006%

    No Known Activations