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

    Neuronpedia

    INDEX
    Explanations

    random strings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Eclipse
    -0.07
     eiusmod
    -0.06
    ip
    -0.06
    Estado
    -0.06
     embassy
    -0.06
     biochemical
    -0.06
     birey
    -0.06
     throat
    -0.06
     полот
    -0.06
     numerical
    -0.06
    POSITIVE LOGITS
    →→
    0.07
    enthal
    0.07
    gars
    0.07
    =~
    0.07
    แท
    0.06
     pathlib
    0.06
    4
    0.06
    менш
    0.06
    74
    0.06
     infancy
    0.06
    Act Density 0.015%

    No Known Activations