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

    Neuronpedia

    INDEX
    Explanations

    quotation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hip
    -0.06
     Afro
    -0.06
     техні
    -0.06
     дві
    -0.06
     ST
    -0.06
    乌
    -0.06
    -sided
    -0.06
    stk
    -0.06
     Rack
    -0.06
     Mech
    -0.06
    POSITIVE LOGITS
    _recommend
    0.07
    =message
    0.07
    첨부
    0.07
    مش
    0.07
    txn
    0.06
    ewire
    0.06
    Instantiate
    0.06
    ��
    0.06
    berra
    0.06
    -finals
    0.06
    Act Density 0.013%

    No Known Activations