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

    Neuronpedia

    INDEX
    Explanations

    Code steps

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    리로
    -0.06
     tim
    -0.06
    Channel
    -0.06
    921
    -0.06
    ouchers
    -0.06
    87
    -0.06
    Ge
    -0.06
    909
    -0.06
     TMP
    -0.06
     Bog
    -0.06
    POSITIVE LOGITS
     stocks
    0.07
    categoria
    0.07
     enums
    0.06
     Petit
    0.06
     جای
    0.06
     perpetrated
    0.06
     cipher
    0.06
     окрем
    0.06
    _CLOSED
    0.06
     minul
    0.06
    Act Density 0.059%

    No Known Activations