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

    Neuronpedia

    INDEX
    Explanations

    with/without

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Density
    -0.07
    '_
    -0.07
     originates
    -0.06
     Grow
    -0.06
    ({...
    -0.06
    }`);↵↵
    -0.06
    :not
    -0.06
    _Connection
    -0.06
     significant
    -0.06
    ())[
    -0.06
    POSITIVE LOGITS
    alten
    0.07
    _UNICODE
    0.07
    _USERS
    0.06
    .bid
    0.06
    laden
    0.06
    =create
    0.06
    ếp
    0.06
     любой
    0.06
     depart
    0.06
    ssf
    0.06
    Act Density 0.194%

    No Known Activations