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

    Neuronpedia

    INDEX
    Explanations

    varied topics and assistance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     teams
    -0.07
     Role
    -0.07
     Pool
    -0.07
     Vitamin
    -0.06
     departments
    -0.06
     Each
    -0.06
     NR
    -0.06
     occurrence
    -0.06
    健康
    -0.06
     QUESTION
    -0.06
    POSITIVE LOGITS
    ‚Ì
    0.06
     علی
    0.06
    relu
    0.06
    .unlink
    0.06
     المس
    0.05
     زیاد
    0.05
    679
    0.05
    Politics
    0.05
    íveis
    0.05
     ‎
    0.05
    Act Density 0.069%

    No Known Activations