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

    Neuronpedia

    INDEX
    Explanations

    Bob

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ，其
    -0.07
     Engl
    -0.07
    lyn
    -0.06
     mej
    -0.06
     strtol
    -0.06
     Extr
    -0.06
    #",
    -0.06
     �
    -0.06
     tran
    -0.06
     requ
    -0.06
    POSITIVE LOGITS
    Bob
    0.16
     Bob
    0.16
     bob
    0.14
     Alice
    0.12
    Alice
    0.12
    bob
    0.10
    باب
    0.08
     alice
    0.08
     Jim
    0.08
    bos
    0.08
    Act Density 0.003%

    No Known Activations