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

    Neuronpedia

    INDEX
    Explanations

    informal text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     yazar
    -0.07
     rootNode
    -0.07
    <?=
    -0.06
    ภายใน
    -0.06
     onFailure
    -0.06
     सह
    -0.06
    普通
    -0.06
    市场
    -0.06
     празд
    -0.06
     территории
    -0.06
    POSITIVE LOGITS
    ême
    0.07
    tors
    0.07
     hunting
    0.06
    Listening
    0.06
    emp
    0.06
    ائ
    0.06
     Mend
    0.06
    maint
    0.06
     finder
    0.06
     PROCESS
    0.06
    Act Density 0.001%

    No Known Activations