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

    Neuronpedia

    INDEX
    Explanations

    We

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Close
    -0.07
     hurt
    -0.07
     shield
    -0.06
     emitter
    -0.06
     structures
    -0.06
     sym
    -0.06
     Eight
    -0.06
     fund
    -0.06
     policym
    -0.06
     inst
    -0.06
    POSITIVE LOGITS
    νω
    0.07
    :Add
    0.06
    vat
    0.06
     principales
    0.06
     herkes
    0.06
    /exp
    0.06
    UPDATED
    0.06
     Loài
    0.06
     Kremlin
    0.06
     пода
    0.06
    Act Density 0.047%

    No Known Activations