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

    Neuronpedia

    INDEX
    Explanations

    any

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dwarf
    -0.07
    -note
    -0.06
     letto
    -0.06
    oster
    -0.06
    olith
    -0.06
     控
    -0.06
     сторону
    -0.06
    ++]=
    -0.06
    anteed
    -0.06
     คน
    -0.06
    POSITIVE LOGITS
    .HtmlControls
    0.06
    _Game
    0.06
    (touch
    0.06
     Crunch
    0.06
    Own
    0.06
    तर
    0.06
     мир
    0.06
    _en
    0.06
    .Di
    0.06
    .Man
    0.06
    Act Density 0.014%

    No Known Activations