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

    Neuronpedia

    INDEX
    Explanations

    code/data entries

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     відбува
    -0.07
     Organic
    -0.07
    og
    -0.07
    adden
    -0.07
     FAC
    -0.07
    zk
    -0.07
     dib
    -0.06
    코
    -0.06
    ihat
    -0.06
    templ
    -0.06
    POSITIVE LOGITS
    [unit
    0.06
     mont
    0.06
    .lua
    0.06
    canf
    0.06
    .Expression
    0.06
    callee
    0.06
    ρον
    0.06
    单位
    0.06
    Immediate
    0.06
     ApiException
    0.06
    Act Density 0.015%

    No Known Activations