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

    Neuronpedia

    INDEX
    Explanations

    that

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    //----------------------------------------------------------------------------------------------------------------
    -0.06
     dần
    -0.06
    .getInstance
    -0.06
    scopes
    -0.06
    れ
    -0.06
    Gem
    -0.06
    альными
    -0.06
     новые
    -0.06
     Наз
    -0.06
    letters
    -0.06
    POSITIVE LOGITS
     DEF
    0.07
    rientation
    0.06
    etermined
    0.06
    _sim
    0.06
    _factory
    0.06
     Presentation
    0.06
    /><
    0.06
    -screen
    0.06
    tokenId
    0.06
     accomplishments
    0.06
    Act Density 0.065%

    No Known Activations