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

    Neuronpedia

    INDEX
    Explanations

    5

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     clustering
    -0.07
     ниже
    -0.07
    utivo
    -0.06
     valido
    -0.06
     �
    -0.06
     abaixo
    -0.06
     benefited
    -0.06
     →
    -0.06
     Commun
    -0.06
    ρο
    -0.06
    POSITIVE LOGITS
    
    0.08
    5
    0.07
     ')↵
    0.07
    "]);
↵
    0.07
    ForSegue
    0.07
    AsyncResult
    0.07
    ori
    0.07
     lineWidth
    0.07
    ELSE
    0.07
    515
    0.07
    Act Density 0.008%

    No Known Activations