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

    Neuronpedia

    INDEX
    Explanations

    technical documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cuis
    -0.07
     sunk
    -0.07
     Whats
    -0.06
     Constitution
    -0.06
    <input
    -0.06
     telefono
    -0.06
     Def
    -0.06
     stole
    -0.06
     constitution
    -0.06
     OK
    -0.06
    POSITIVE LOGITS
    abyrin
    0.07
    scious
    0.07
     Yi
    0.06
    lijke
    0.06
    ans
    0.06
    میر
    0.06
     süreç
    0.06
    obbled
    0.06
    enment
    0.06
    ByExample
    0.06
    Act Density 0.000%

    No Known Activations