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

    Neuronpedia

    INDEX
    Explanations

    ary

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    狐
    -0.07
    ?id
    -0.07
     משה
    -0.07
    书
    -0.07
     <!--<
    -0.06
    ><
    -0.06
    cheng
    -0.06
    .JSON
    -0.06
    Sets
    -0.06
    ]<
    -0.06
    POSITIVE LOGITS
    战术
    0.08
     ess
    0.07
     witness
    0.07
    stood
    0.07
    重要意义
    0.07
     שנים
    0.07
    ATORY
    0.07
    reas
    0.07
     Domin
    0.07
     HT
    0.07
    Act Density 0.001%

    No Known Activations