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

    Neuronpedia

    INDEX
    Explanations

    define

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    InBackground
    -0.07
    .pid
    -0.07
    -production
    -0.07
     {!!
    -0.06
    (selection
    -0.06
    |"
    -0.06
    Parsed
    -0.06
    番
    -0.06
     mas
    -0.06
     reserva
    -0.06
    POSITIVE LOGITS
    ,H
    0.07
     commits
    0.06
    ,D
    0.06
    .Ch
    0.06
    INS
    0.06
    ,S
    0.06
    ону
    0.06
    DE
    0.06
    /person
    0.06
    аліз
    0.06
    Act Density 0.001%

    No Known Activations