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

    Neuronpedia

    INDEX
    Explanations

    applicant

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tavern
    -0.06
     ⟨
    -0.06
    ----------------------------------------------------------------------------
    -0.06
    version
    -0.06
     wf
    -0.06
    measure
    -0.06
     люд
    -0.06
    센터
    -0.06
     chees
    -0.06
     irrespective
    -0.06
    POSITIVE LOGITS
     chave
    0.07
    (callback
    0.06
    (hdc
    0.06
     input
    0.06
    醫
    0.06
    Diagram
    0.06
     каз
    0.06
    (',
    0.06
    LIB
    0.06
     ก
    0.06
    Act Density 0.003%

    No Known Activations