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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    22
    -0.08
     array
    -0.07
     rocket
    -0.07
     Solar
    -0.07
    u
    -0.07
     currentNode
    -0.07
    797
    -0.07
    PropertyValue
    -0.07
    202
    -0.06
     Portland
    -0.06
    POSITIVE LOGITS
            
↵        
↵
    0.08
    .he
    0.07
     gh
    0.07
    .IM
    0.07
     hold
    0.07
    FFE
    0.07
    敬
    0.07
     fitte
    0.07
    �
    0.06
     киш
    0.06
    Act Density 0.141%

    No Known Activations