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

    Neuronpedia

    INDEX
    Explanations

    "or" and common articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     thereafter
    -0.09
     inferior
    -0.09
     edelleen
    -0.08
     urge
    -0.08
     afterwards
    -0.08
     breasts
    -0.08
     hopefully
    -0.08
     possibly
    -0.08
     möglicherweise
    -0.07
    tdown
    -0.07
    POSITIVE LOGITS
     anecdotes
    0.11
     experi
    0.09
     Dias
    0.09
     insider
    0.08
     annivers
    0.08
    Dias
    0.08
     άλλη
    0.08
     EXPERI
    0.08
     તસવી
    0.08
    .money
    0.08
    Act Density 0.028%

    No Known Activations