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

    Neuronpedia

    INDEX
    Explanations

    executable files

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Immediate
    -0.07
     Cream
    -0.06
    ']))↵
    -0.06
     immediate
    -0.06
     weights
    -0.06
    Sale
    -0.06
     ze
    -0.06
     özelliği
    -0.06
    !!)↵
    -0.06
    脑
    -0.06
    POSITIVE LOGITS
    ,output
    0.07
    拜
    0.07
     trilogy
    0.06
     relent
    0.06
    /testify
    0.06
    _mut
    0.06
    .limit
    0.06
    pellier
    0.06
    慎
    0.06
    Field
    0.06
    Act Density 0.025%

    No Known Activations