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
     مار
    -0.07
    rogram
    -0.07
     ilç
    -0.07
     조금
    -0.07
     rankings
    -0.07
     действительно
    -0.06
     Чи
    -0.06
     преж
    -0.06
     سوم
    -0.06
     mně
    -0.06
    POSITIVE LOGITS
     system
    0.07
     системы
    0.07
    pta
    0.07
    basis
    0.07
    _service
    0.06
    _rp
    0.06
    _Q
    0.06
    cept
    0.06
     LM
    0.06
     системи
    0.06
    Act Density 0.015%

    No Known Activations