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

    Neuronpedia

    INDEX
    Explanations

    term

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     term
    -2.61
     Term
    -1.63
    Term
    -1.38
    term
    -1.31
     TERM
    -1.31
     término
    -1.23
     terme
    -1.19
     word
    -1.09
    TERM
    -0.94
     phrase
    -0.89
    POSITIVE LOGITS
     goutte
    0.65
     soeur
    0.61
     rossa
    0.60
     Constitucional
    0.60
     marinho
    0.57
     regiments
    0.57
     revient
    0.56
     republics
    0.56
    MigrationBuilder
    0.56
     oignon
    0.56
    Act Density 0.193%

    No Known Activations