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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Dj
    -0.08
    .realm
    -0.07
     Loren
    -0.07
    ​​
    -0.06
     лож
    -0.06
     cst
    -0.06
     budeme
    -0.06
    _Destroy
    -0.06
    uvo
    -0.06
    decoded
    -0.06
    POSITIVE LOGITS
     opens
    0.07
    _age
    0.06
    .btn
    0.06
    (Output
    0.06
     opened
    0.06
     gigs
    0.06
     Can
    0.06
    .out
    0.06
    .lista
    0.06
    chan
    0.06
    Act Density 0.006%

    No Known Activations