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

    Neuronpedia

    INDEX
    Explanations

    .add

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Bobby
    -0.06
     confession
    -0.06
     měsíce
    -0.06
    ่อม
    -0.06
    _PRE
    -0.06
    层
    -0.06
    _z
    -0.06
     faz
    -0.06
    .visibility
    -0.06
     Sha
    -0.06
    POSITIVE LOGITS
    (LocalDate
    0.07
     Ahead
    0.07
     Achie
    0.07
     pooled
    0.07
    .lastName
    0.06
     earns
    0.06
    فش
    0.06
    ])]↵
    0.06
    мотреть
    0.06
     offer
    0.06
    Act Density 0.005%

    No Known Activations