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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Advisor
    -0.07
     rơi
    -0.07
     chạm
    -0.07
    ections
    -0.07
     Alberto
    -0.07
     aimed
    -0.07
    ⟱
    -0.07
    注意
    -0.07
     Phillip
    -0.07
     Claude
    -0.07
    POSITIVE LOGITS
     discharged
    0.07
    Proof
    0.07
     Encyclopedia
    0.07
     wah
    0.07
    rh
    0.06
    /reset
    0.06
    $t
    0.06
    ｔ
    0.06
    )/
    0.06
     ra
    0.06
    Act Density 0.069%

    No Known Activations