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

    Neuronpedia

    INDEX
    Explanations

    mixed languages and code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Folders
    -0.06
     encourages
    -0.06
     формы
    -0.06
     kinky
    -0.06
     beam
    -0.06
     Therefore
    -0.06
    Chooser
    -0.06
     integrated
    -0.06
     mower
    -0.06
     Those
    -0.06
    POSITIVE LOGITS
    _pref
    0.07
    験
    0.07
     collections
    0.07
     signup
    0.06
     refreshToken
    0.06
    inct
    0.06
     consist
    0.06
     водой
    0.06
     lending
    0.06
     Mitt
    0.06
    Act Density 0.008%

    No Known Activations