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

    Neuronpedia

    INDEX
    Explanations

    Orientation/Position

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    quarter
    -0.06
    Nullable
    -0.06
     seconds
    -0.06
     gitti
    -0.06
     verbess
    -0.06
    undaki
    -0.06
    ookie
    -0.06
     Ogre
    -0.06
     kriz
    -0.06
     student
    -0.05
    POSITIVE LOGITS
    貸
    0.07
     Sanchez
    0.07
    思
    0.06
     attitude
    0.06
    eways
    0.06
     lam
    0.06
    ��
    0.06
     ابراه
    0.06
    ceptive
    0.06
    脑
    0.06
    Act Density 0.068%

    No Known Activations