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

    Neuronpedia

    INDEX
    Explanations

    recess

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     harm
    -0.07
     lik
    -0.06
    途
    -0.06
    Birth
    -0.06
    ить
    -0.06
    \:
    -0.06
    _input
    -0.06
    webdriver
    -0.06
    _Integer
    -0.06
    PyObject
    -0.06
    POSITIVE LOGITS
     dropout
    0.07
    byterian
    0.07
     badges
    0.07
    dued
    0.07
    (status
    0.07
    政策
    0.07
     depressing
    0.07
    מועד
    0.07
    设备
    0.07
    upos
    0.07
    Act Density 0.003%

    No Known Activations