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

    Neuronpedia

    INDEX
    Explanations

    treatment outcomes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     دم
    -0.07
     spree
    -0.06
    Hall
    -0.06
     Crush
    -0.06
    SmartyHeaderCode
    -0.06
    ОН
    -0.06
     Rx
    -0.06
    724
    -0.06
     ropes
    -0.06
    Drop
    -0.06
    POSITIVE LOGITS
               ↵
    0.07
    !')↵
    0.06
    ↵↵
    0.06
     <->
    0.06
     angels
    0.06
     añ
    0.06
     sca
    0.06
    いつ
    0.06
     nä
    0.06
    kel
    0.06
    Act Density 0.148%

    No Known Activations