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

    Neuronpedia

    INDEX
    Explanations

    prepositions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    enthal
    -0.07
    Assertions
    -0.07
    _NEAREST
    -0.06
    /cli
    -0.06
     Otherwise
    -0.06
     sensors
    -0.06
     ژ
    -0.06
     discourage
    -0.06
    zej
    -0.06
     個
    -0.06
    POSITIVE LOGITS
    [action
    0.07
     över
    0.06
     Albuquerque
    0.06
    ُس
    0.06
    _units
    0.06
     fot
    0.06
    ened
    0.06
     una
    0.06
    _bonus
    0.06
     borderWidth
    0.06
    Act Density 0.057%

    No Known Activations