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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Hal
    -0.07
    foobar
    -0.06
     hacker
    -0.06
     cca
    -0.06
    _entities
    -0.06
     Hal
    -0.06
     ifade
    -0.06
     lower
    -0.06
    ?");↵
    -0.06
    tot
    -0.06
    POSITIVE LOGITS
     OPTION
    0.07
     them
    0.06
     गत
    0.06
     ethereum
    0.06
    .Standard
    0.06
     getName
    0.06
     вос
    0.06
    _THEME
    0.06
     площад
    0.06
     соп
    0.06
    Act Density 0.005%

    No Known Activations