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

    Neuronpedia

    INDEX
    Explanations

    front

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _note
    -0.07
    Io
    -0.07
     councillors
    -0.07
    (vol
    -0.07
     butcher
    -0.07
     kube
    -0.06
    Disk
    -0.06
    Salary
    -0.06
     DBG
    -0.06
     disk
    -0.06
    POSITIVE LOGITS
    :url
    0.07
     pics
    0.07
     bestselling
    0.06
    μοί
    0.06
    arya
    0.06
    rom
    0.06
    .web
    0.06
     necessity
    0.06
    /local
    0.06
    -picture
    0.06
    Act Density 0.003%

    No Known Activations