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

    Neuronpedia

    INDEX
    Explanations

    2

    np_max-act · gemini-2.0-flash

    The neuron never fires—it doesn’t detect any pattern in these inputs.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    bv
    -0.07
    ัวหน
    -0.07
     closets
    -0.06
    áč
    -0.06
     rumored
    -0.06
    London
    -0.06
     ":"
    -0.06
     Ub
    -0.06
     memb
    -0.06
    Homepage
    -0.06
    POSITIVE LOGITS
    сім
    0.07
    __(*
    0.07
    .UseVisualStyleBackColor
    0.06
     которой
    0.06
     createState
    0.06
    -fw
    0.06
    .elasticsearch
    0.06
    >;
    0.06
    ілля
    0.06
    /ioutil
    0.06
    Act Density 0.001%

    No Known Activations