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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Tout
    -0.07
     CHANGE
    -0.06
     wax
    -0.06
    kube
    -0.06
    ね
    -0.06
    酒
    -0.06
    Website
    -0.06
     retrieve
    -0.06
     fenced
    -0.06
     totalTime
    -0.05
    POSITIVE LOGITS
    řit
    0.07
     catastrophe
    0.06
    až
    0.06
     suppliers
    0.06
    闘
    0.06
     markdown
    0.06
     Olympus
    0.06
    APON
    0.06
    .setVisible
    0.06
    Capabilities
    0.06
    Act Density 0.000%

    No Known Activations