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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    itates
    -0.07
    真是
    -0.06
     ==↵
    -0.06
    iph
    -0.06
    ्स
    -0.06
    inces
    -0.06
     aggress
    -0.06
     liegt
    -0.06
    ��
    -0.06
     verschied
    -0.06
    POSITIVE LOGITS
     tabela
    0.07
     Rectangle
    0.07
     coment
    0.07
     enqu
    0.07
    Insert
    0.06
     Greenwich
    0.06
     тру
    0.06
    _UD
    0.06
     SCALE
    0.06
    //------------------------------------------------------------------------------------------------
    0.06
    Act Density 0.012%

    No Known Activations