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

    Neuronpedia

    INDEX
    Explanations

    actions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    igi
    -0.07
    _company
    -0.06
     machine
    -0.06
     oven
    -0.06
     bộ
    -0.06
     engine
    -0.06
    ebiliriz
    -0.06
    /un
    -0.06
     circuit
    -0.06
    nell
    -0.06
    POSITIVE LOGITS
    (resourceName
    0.06
     kayıt
    0.06
    .vx
    0.06
     fearful
    0.06
    <Scalars
    0.06
     "'.$
    0.06
    /'.$
    0.05
    :last
    0.05
     иск
    0.05
    (',',$
    0.05
    Act Density 0.308%

    No Known Activations