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

    Neuronpedia

    INDEX
    Explanations

    expressing not caring

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ij
    -0.08
    ってる
    -0.07
    tığımız
    -0.07
     jeste
    -0.07
     droit
    -0.07
    �
    -0.07
    avec
    -0.07
    :return
    -0.07
    _jwt
    -0.07
    foo
    -0.07
    POSITIVE LOGITS
    (Conv
    0.08
     Mile
    0.07
     rent
    0.07
     groupId
    0.07
     SC
    0.07
     Brend
    0.07
    (dr
    0.07
    prints
    0.07
     vari
    0.07
    lund
    0.06
    Act Density 0.033%

    No Known Activations