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

    Neuronpedia

    INDEX
    Explanations

    programming code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     halls
    -0.07
     alleges
    -0.06
     beaches
    -0.06
    ruž
    -0.06
    }'",
    -0.06
    ven
    -0.06
     driv
    -0.06
    repository
    -0.06
     близько
    -0.06
     ESL
    -0.06
    POSITIVE LOGITS
    \Category
    0.07
     dicho
    0.06
               ↵
    0.06
    ^^^^
    0.06
    評
    0.06
     أول
    0.06
    bounce
    0.06
    �
    0.06
     offline
    0.06
     côté
    0.06
    Act Density 0.022%

    No Known Activations