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

    Neuronpedia

    INDEX
    Explanations

    your

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    De
    -0.07
    ाकर
    -0.07
    $/,↵
    -0.06
     begs
    -0.06
     форму
    -0.06
     Tan
    -0.06
    \Object
    -0.06
     Rath
    -0.06
    plits
    -0.06
    -0.06
    POSITIVE LOGITS
     factory
    0.07
     tük
    0.07
     THB
    0.07
     Auxiliary
    0.06
     Feder
    0.06
    .mu
    0.06
     receivers
    0.06
     Guidance
    0.06
     yabancı
    0.06
     AUX
    0.06
    Act Density 0.391%

    No Known Activations