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

    Neuronpedia

    INDEX
    Explanations

    miscellaneous text snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     chairs
    -0.08
     acrylic
    -0.07
    ✔
    -0.07
    asar
    -0.07
    mania
    -0.07
     AI
    -0.07
     patriarch
    -0.07
    國
    -0.07
    aal
    -0.07
     SYN
    -0.06
    POSITIVE LOGITS
     Fleet
    0.07
    .keep
    0.06
     olmadığı
    0.06
    rieved
    0.06
     freeing
    0.06
    _disconnect
    0.06
    solid
    0.06
     Republic
    0.06
     ensure
    0.06
     freezing
    0.06
    Act Density 0.000%

    No Known Activations