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

    Neuronpedia

    INDEX
    Explanations

    masked data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     automation
    -0.07
     Automation
    -0.07
    ुमत
    -0.07
    票
    -0.07
     任
    -0.07
     Dra
    -0.07
    halt
    -0.06
    Elim
    -0.06
    恶
    -0.06
    							
↵
    -0.06
    POSITIVE LOGITS
     refunds
    0.07
    getReference
    0.07
     �
    0.06
     JetBrains
    0.06
     nicknamed
    0.06
    Inicial
    0.06
     biraz
    0.06
     paper
    0.06
     resent
    0.06
    ße
    0.06
    Act Density 0.031%

    No Known Activations