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

    Neuronpedia

    INDEX
    Explanations

    And

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    book
    -0.07
    _DO
    -0.07
     接
    -0.06
    aghetti
    -0.06
    piration
    -0.06
    μές
    -0.06
    thin
    -0.06
    ò
    -0.06
    弱
    -0.06
    avery
    -0.06
    POSITIVE LOGITS
    '/>
    0.07
     gestion
    0.07
    .variables
    0.06
    抗
    0.06
     Mehr
    0.06
    .Object
    0.06
    ieren
    0.06
    /gcc
    0.06
    URATION
    0.06
    afb
    0.06
    Act Density 0.000%

    No Known Activations