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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    яч
    -0.07
    Model
    -0.07
    .Range
    -0.07
     community
    -0.06
    "M
    -0.06
    constant
    -0.06
    Environment
    -0.06
    Cele
    -0.06
     corrupt
    -0.06
    married
    -0.06
    POSITIVE LOGITS
    _ASSERT
    0.07
     웹
    0.06
    (plan
    0.06
     graphs
    0.06
     doInBackground
    0.06
     Explanation
    0.06
    콜걸
    0.06
     hated
    0.06
     unnatural
    0.06
    enet
    0.06
    Act Density 0.078%

    No Known Activations