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

    Neuronpedia

    INDEX
    Explanations

    Code contracts/specifications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Could
    -0.07
     ויש
    -0.07
    (company
    -0.07
    Medical
    -0.07
    ул
    -0.07
    Could
    -0.07
    כל
    -0.07
     complains
    -0.06
    character
    -0.06
    ð
    -0.06
    POSITIVE LOGITS
    ᐂ
    0.08
     Aurora
    0.08
    两人
    0.07
    agate
    0.07
    $app
    0.07
     Orth
    0.07
     Petsc
    0.07
    .my
    0.07
    分开
    0.06
     citiz
    0.06
    Act Density 0.010%

    No Known Activations