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

    Neuronpedia

    INDEX
    Explanations

    backup

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Bin
    -0.08
     النبات
    -0.08
     fruto
    -0.08
    air
    -0.08
    �
    -0.08
     impulso
    -0.08
    inci
    -0.07
    bli
    -0.07
    pairs
    -0.07
     Bao
    -0.07
    POSITIVE LOGITS
     rotor
    0.08
    erecht
    0.08
    .activ
    0.08
     proble
    0.08
     ersetzen
    0.08
     Tyson
    0.07
     Entire
    0.07
     Ster
    0.07
     ------------------------------------------------
    0.07
    (Client
    0.07
    Act Density 0.006%

    No Known Activations