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

    Neuronpedia

    INDEX
    Explanations

    math problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    )&&(
    -0.07
     inout
    -0.07
    Explorer
    -0.06
    }"↵
    -0.06
    externalActionCode
    -0.06
     Floyd
    -0.06
    _STR
    -0.06
     Femin
    -0.06
    pix
    -0.06
    _Record
    -0.06
    POSITIVE LOGITS
     Interested
    0.07
    >?
    0.07
    ΗΜΑ
    0.06
     Trotsky
    0.06
     Apostle
    0.06
    lain
    0.06
     Spencer
    0.06
     dello
    0.06
    _SMS
    0.06
     jardin
    0.06
    Act Density 0.143%

    No Known Activations