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

    Neuronpedia

    INDEX
    Explanations

    v

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     thousands
    -0.07
    ICIAL
    -0.06
     interoper
    -0.06
     qi
    -0.06
     multi
    -0.06
     roster
    -0.06
     EXIT
    -0.06
     현대
    -0.06
    anghai
    -0.06
     MATRIX
    -0.06
    POSITIVE LOGITS
    ắc
    0.07
    ():
↵
    0.07
     بودند
    0.07
     Minerals
    0.06
    addGroup
    0.06
    为什么
    0.06
    ilmektedir
    0.06
    öyle
    0.06
    /pm
    0.06
    …the
    0.06
    Act Density 0.017%

    No Known Activations