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

    Neuronpedia

    INDEX
    Explanations

    missions and retrieval

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    USE
    -0.08
    Abstract
    -0.08
    879
    -0.08
    AV
    -0.08
    757
    -0.07
    626
    -0.07
    IFICATE
    -0.07
    νο
    -0.07
    ARGV
    -0.07
     تھی
    -0.07
    POSITIVE LOGITS
     regreso
    0.12
    返回
    0.12
     लौट
    0.12
     返回
    0.11
    .Return
    0.11
    (return
    0.11
     वापस
    0.11
    .return
    0.11
     добы
    0.11
    回来
    0.10
    Act Density 0.035%

    No Known Activations